MCP servers for ai-agent

runs anywhere. uses anything

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Loops (auto-research) and more. #dsh

Local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.

MCP server: repo map, code search, and token-aware context packs for AI coding agents

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.

Revenue-first website analytics installed and verified by AI agents through MCP

🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node.

Android device bridge for Claude Code via MCP + Shizuku. No root, no model polling.

Give the agent "this" and he gets a real PC.

Turn tab overload into a local-first workspace with intent-first AI organization and Agent collaboration through MCP.

A floating chat bubble that lets Claude Code, Codex or OpenCode use your Android phone. Runs inside the app on your own subscription or free models. No adb, no PC, no root.

Local-first AI workbench for DSH Plugins, combining Agent sessions, project files, data analysis, web research, MCP, and Office artifacts in an Electron desktop app.

🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill s

Context compression for MCP. Same upstream call, exact results recoverable.

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

麦当劳 MCP 全能助手 | 全覆盖 35 个工具 · 7 大工作流 · 14 条防错铁律 | 领券 / 点餐 / 外送 / 派对预约 / 积分到期止损，附零依赖 CLI 通道

Terminal discovery hub and package manager for AI coding tools, MCP servers, and agent skills. Built with Python & Textual

MCP server for git repositories: local git in-process via gitoxide, plus GitHub, GitLab, Gitea and Forgejo through their CLIs

把你的麦当劳积分和优惠券当成一份资产来管：折算人民币现值、排出最优兑换出口、量化过期风险，并给出可执行的兑换路径。

🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workf

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

MCP server for ICTFax — list and track faxes, upload documents and send faxes over ICTCore REST. By ICT Innovations.

MCP server for ICTContact / ICTDialer — monitor outbound campaigns and start/stop them. By ICT Innovations.

MCP server for ICTDialer — monitor cloud auto-dialer campaigns and start/stop them. By ICT Innovations.

MCP server for ICTBroadcast — monitor outbound voice/SMS/fax campaigns and start/stop them. By ICT Innovations.

Read-only MCP server for ICTPBX — extensions, DIDs, SIP trunks, tenants and PBX statistics over ICTCore REST. By ICT Innovations.

MCP server for ICTExam — read exams, gradebooks and item analysis; parse papers with AI and publish exams. By ICT Innovations.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace

DSH (DeepSeek Harness) plugin that launches and drives a running Godot 4.x game through its in-game TCP interaction server — replaces the godot-mcp MCP server with native agent tools.

MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads

Universal Agent Plugin for safe BLE diagnostics and automation, with Agent Plugins 1.0.0 metadata, a portable Skill, deterministic CLI, local MCP, and evidence capture/diff/replay.

MCP server that lets your AI assistant read and write Figma in real time — no API token, no rate limits. Works with Claude, Cursor, Copilot, Codex and any MCP client.

Free AI-powered Amazon product research & marketplace intelligence for 6 platforms. Hidden Profit Index — Sorftime's proprietary algorithm for finding overlooked high-margin products. 80+ MCP tools. A

Agentic web crawler with headless browser orchestration & anti-bot bypass

Vision LLM flowchart, diagram & document structure parser to Mermaid

Real-time voice accent normalization, dialect adaptation & stream enhancer

Automated codebase architectural debt analyzer & refactoring planner

Cross-platform e-commerce inventory sync & purchase order agent

Autonomous deep research planner & executive report synthesizer

AI regulatory compliance, export control directive & safety audit scanner

Dynamic LLM router for complexity, latency & token cost optimization

AI-powered smart calendar scheduling, conflict resolution & deep work optimizer

Intelligent LLM API cost analyzer, model tier selector & monthly spend optimizer

Meeting transcript intelligent summarizer & action item extractor

In-browser code sandbox, live web-container runner & instant UI renderer

AI-moderated user research interview conductor & affinity diagram builder

Full-duplex real-time streaming voice agent with barge-in detection

Multi-attribute product spec comparison & review sentiment analyzer

Real-time zero-shot voice cloning & emotional neural TTS generator

Enterprise codebase AST parsing, semantic vector indexing & symbol graph

Visual flow node-graph to executable Python DAG workflow generator

Complex PDF/Image OCR, table layout parser & structured JSON extractor

Multimodal image-to-video motion control & camera trajectory animator

Expose DeepSeek Harness agent capabilities as an MCP server (brain=Hermes, arms=Harness)

MCP server and CLI that let AI agents (Claude, Codex, any MCP client) see and drive a running WARUDO: scene, assets, character pose and IK, expressions, blueprints, camera and captures.

Free live chat and AI support agent. Set it up from Claude Code, Cursor, ChatGPT, or Grok. No signup.

Tracking my journey into AI engineering, one module at a time. Fundamentals to agents, with hands-on projects. Open to all.

Multi-agent creative studio for copy & marketing campaign asset generation

AI LLM visibility tracker monitoring brand share of voice (Lettertrace style)

Vibe coding IDE extension helper providing real-time code completion

Proactive executive AI assistant for autonomous task scheduling (Hey Noah style)

Real-time AI agent execution observability & token tracing (Progress AI style)

Hardware voice recorder audio processor & task dispatcher (SecondBrain style)

Real-world AI task evaluation & custom benchmark runner (oqoqo style)

AI Gateway proxy router, rate limiting & PII masking engine (ngrok style)

Responsible & ESG investment portfolio analyzer (Portfolio Lab style)

AI coding agent context compressor & cost reducer (Paritok style)

dMoERA Creator Studio MCP Server: build, backtest, and deploy crypto trading strategies via AI agents

天枢 × AI-Agent 编排 MCP server：把 其他AI-Agent 当作执行工人，自动完成「开发 → 验收 → 失败返修 → 再验收」闭环。

Deterministic AST tool-call schema auto-repair & parameter projection guard (AutoGen / LangGraph)

Multimodal OCR table grid & merged-cell reconstruction into Markdown (MinerU / Marker)

Cross-border Geo-IP currency converter & dynamic VAT/tax nexus calculator (Stripe Tax)

Zero-dependency heuristic adversarial prompt injection & override neutralizer (Lakera / NeMo)

Long-horizon conversational memory compaction & episodic anchor extractor (Mem0 / LangMem)

Deterministic JSON schema extraction and coercing engine for product hardware

Real-time in-memory unified diff & change telemetry generator for live artifacts

Multi-perspective synthetic consumer focus group simulator for market sentiment

Dynamic search synthesis and Sparkpage layout compiler generating comparison matrices & HTML UI

Autonomous multi-stage prompt-to-DAG planner resolving dependency topologies

Dynamic intent and budget-aware multi-model Pareto router selecting from 70+ LLMs

Autonomous web browser action planner mapping goals into resilient selector action sequences

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

Deep research multi-source consensus arbitration engine evaluating authority & contradictions

Deep research multi-source cross-citation graph analyzer and consensus resolver

Adaptive token bucket concurrency rate limiter and backoff scheduler preventing HTTP 429 exceptions

Reciprocal Rank Fusion (RRF) and hybrid search rank fusion engine

E-commerce advertising policy scanner detecting prohibited claims and trademarks

Query-guided contextual document compression engine pruning irrelevant web noise

Autonomous web checkout form field analyzer and heuristic autofill engine resolving buyer parameters

Minimal JSON Patch (RFC 6902) operational differential engine supporting atomic state sync

Stateful workflow checkpoint manager calculating state hashes and rollback points

Real-time acoustic noise floor estimator and spectral gate suppressing ambient reverberation

Semantic prompt cache deduplicator calculating Jaccard token overlap to prevent redundant LLM cost

Multimodal visual spec grounding engine calculating physical dimensions and DoF

Dynamic price elasticity of demand calculator deriving marginal revenue maxima

Dynamic session context window tokenizer and dialogue compaction manager

Multi-tenant security isolation guard enforcing memory boundary compartmentalization

Customer lead scoring and interaction velocity evaluator predicting conversions

Generative Schema.org Product and FAQPage JSON-LD rich snippet generator

Categorized index of 718 public GenPark AI agent skills, with tested Python packages and MCP integrations.

Email MCP server for AI agents - full mailbox access for Claude, Codex, Cursor or any MCP client: search, read, send, attachments, folders across Gmail, Outlook, iCloud, QQ, 163 and any IMAP/SMTP host

Vision-to-DOM element anchor resilient against click drift (Genspark Claw / Computer Use)

Multi-agent debate cross-examination & consensus arbitration (Super Agent / DeepSeek-R1)

Long-horizon conversational memory compaction & episodic anchor extractor (Mem0 / LangMem)

Sub-100ms conversational turn-taking & barge-in handler (Cartesia Sonic / ElevenLabs)

Sub-100ms conversational turn-taking & barge-in handler (Cartesia Sonic / ElevenLabs)

Autonomous merchant checkout token & velocity limit guardrail (Agentcard / Stripe)

Heterogeneous search synthesis to interactive comparison layout (Genspark Sparkpages)

Cross-border Geo-IP currency converter & dynamic VAT/tax nexus calculator (Stripe Tax)

Zero-dependency heuristic adversarial prompt injection & override neutralizer (Lakera / NeMo)

Multi-agent debate cross-examination & consensus arbitration (Super Agent / DeepSeek-R1)

Vision-to-DOM element anchor resilient against click drift (Genspark Claw / Computer Use)

Multimodal OCR table grid & merged-cell reconstruction into Markdown (MinerU / Marker)

Deterministic AST tool-call schema auto-repair & parameter projection guard (AutoGen / LangGraph)

Heterogeneous search synthesis to interactive comparison layout (Genspark Sparkpages)

Autonomous merchant checkout token & velocity limit guardrail (Agentcard / Stripe)

Deterministic JSON schema extraction and coercing engine for product hardware

Autonomous web browser action planner mapping goals into resilient selector action sequences

Autonomous multi-stage prompt-to-DAG planner resolving dependency topologies

Deep research multi-source consensus arbitration engine evaluating authority & contradictions

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

Real-time in-memory unified diff & change telemetry generator for live artifacts

Multi-perspective synthetic consumer focus group simulator for market sentiment

Deep research multi-source cross-citation graph analyzer and consensus resolver

Dynamic intent and budget-aware multi-model Pareto router selecting from 70+ LLMs

Dynamic search synthesis and Sparkpage layout compiler generating comparison matrices & HTML UI

Autonomous web checkout form field analyzer and heuristic autofill engine resolving buyer parameters

Adaptive token bucket concurrency rate limiter and backoff scheduler preventing HTTP 429 exceptions

E-commerce advertising policy scanner detecting prohibited claims and trademarks

Stateful workflow checkpoint manager calculating state hashes and rollback points

Query-guided contextual document compression engine pruning irrelevant web noise

Semantic prompt cache deduplicator calculating Jaccard token overlap to prevent redundant LLM cost

Reciprocal Rank Fusion (RRF) and hybrid search rank fusion engine

Minimal JSON Patch (RFC 6902) operational differential engine supporting atomic state sync

Real-time acoustic noise floor estimator and spectral gate suppressing ambient reverberation

Multimodal visual spec grounding engine calculating physical dimensions and DoF

Multi-tenant security isolation guard enforcing memory boundary compartmentalization

Customer lead scoring and interaction velocity evaluator predicting conversions

Generative Schema.org Product and FAQPage JSON-LD rich snippet generator

Dynamic price elasticity of demand calculator deriving marginal revenue maxima

Dynamic session context window tokenizer and dialogue compaction manager

Sentence-level RAG factual grounding and hallucination detection engine

Autonomous refund and dispute arbitration engine validating carrier proofs and policies

Acoustic vocal emotion, prosodic valence, and customer frustration analyzer

Autonomous refund and dispute arbitration engine validating carrier proofs and policies

Cross-category e-commerce product bundle pricing optimizer maximizing AOV

Speculative decoding draft-model verification engine calculating acceptance probabilities

Acoustic vocal emotion, prosodic valence, and customer frustration analyzer

Sentence-level RAG factual grounding and hallucination detection engine

Speculative decoding draft-model verification engine calculating acceptance probabilities

Cross-category e-commerce product bundle pricing optimizer maximizing AOV

Real-time prepaid credit burn velocity tracker calculating runway days, health scores, and upsell triggers inspired by Metronome

Real-time usage event ingestion, multi-tier metric aggregation, and precise invoice calculation engine inspired by Metronome

Side-by-side seat-based, usage-based, and hybrid pricing revenue simulator with elasticity scoring inspired by Metronome

Real-time usage event ingestion, multi-tier metric aggregation, and precise invoice calculation engine inspired by Metronome

Real-time prepaid credit burn velocity tracker calculating runway days, health scores, and upsell triggers inspired by Metronome

Side-by-side seat-based, usage-based, and hybrid pricing revenue simulator with elasticity scoring inspired by Metronome

Multi-persona deliberation and Bayesian weighted consensus engine resolving complex agent decision ambiguities

Biological chronotype and circadian rhythm personal scheduler maximizing deep cognitive analytical output

Real-time spend clarity anomaly detector identifying runaway agent token burn spikes with statistical Z-scores

Protocol schema negotiator and capability handshake engine ensuring secure interoperability between agents

Pre-commit diff safety scanner preventing destructive shell commands, API token leaks, and disk corruptions

Multi-turn autonomous agent trajectory evaluator measuring step redundancy and tool choice efficiency

Fault-tolerant tool execution circuit breaker detecting cascading upstream errors and triggering fallback routing

Multi-agent swarm combinatorial auctioneer decomposing objectives and allocating subtasks based on bids

Executive boundary defense and communication arbitrator deflecting non-urgent real-time interruptions to async channels

Personal cognitive load and attention fragmentation index analyzer restructuring daily agendas into deep work blocks

Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs

Verifiable agent reputation ledger tracking cryptographic task receipts and enforcing slashable staking penalties

Multi-dimensional pricing matrix evaluator resolving dynamic pricing rates across region, SLA tiers, and commitments

Fault-tolerant tool execution circuit breaker detecting cascading upstream errors and triggering fallback routing

Pre-commit diff safety scanner preventing destructive shell commands, API token leaks, and disk corruptions

Long-horizon context window compression and semantic deduplicator eliminating redundant tool outputs

Multi-persona deliberation and Bayesian weighted consensus engine resolving complex agent decision ambiguities

Swarm resource deadlock detector constructing Wait-For-Graphs to detect cycles and trigger preemption

Personal cognitive load and attention fragmentation index analyzer restructuring daily agendas into deep work blocks

Swarm resource deadlock detector constructing Wait-For-Graphs to detect cycles and trigger preemption

Distributed swarm state snapshotting and transactional rollback engine restoring consistent states upon failure

Verifiable agent reputation ledger tracking cryptographic task receipts and enforcing slashable staking penalties

Multi-turn autonomous agent trajectory evaluator measuring step redundancy and tool choice efficiency

Protocol schema negotiator and capability handshake engine ensuring secure interoperability between agents

Multi-dimensional pricing matrix evaluator resolving dynamic pricing rates across region, SLA tiers, and commitments

Real-time spend clarity anomaly detector identifying runaway agent token burn spikes with statistical Z-scores

Multi-agent swarm combinatorial auctioneer decomposing objectives and allocating subtasks based on bids

Distributed swarm state snapshotting and transactional rollback engine restoring consistent states upon failure

Biological chronotype and circadian rhythm personal scheduler maximizing deep cognitive analytical output

Epistemic belief state updater and contradiction detector resolving knowledge graph assertion conflicts

Epistemic belief state updater and contradiction detector resolving knowledge graph assertion conflicts

Mathematical consistency and formula balancing auditor for extracted balance sheets, income statements, and cash flow reports.

Continual few-shot exemplar distiller mining high-scoring execution trajectories into prompt demonstrations

Ebbinghaus forgetting curve auditor calculating retention probabilities and executing garbage collection

Indirect prompt injection sanitizer and delimiter boundary firewall neutralizing embedded command overrides

Adversarial prompt jailbreak detector analyzing framing evasion, hypothetical bypasses, and token smuggling

High-speed document PII redaction and credential sanitizer featuring Luhn credit-card verification, reversible salt hashing, and audit logs.

High-speed document PII redaction and credential sanitizer featuring Luhn credit-card verification, reversible salt hashing, and audit logs.

Adversarial prompt jailbreak detector analyzing framing evasion, hypothetical bypasses, and token smuggling

Two-tier memory consolidation engine distilling ephemeral working memory into persistent episodic knowledge

Real-time acoustic VAD & semantic turn-completion endpoint detector distinguishing mid-sentence hesitation pauses from finished speech turns.

Mathematical consistency and formula balancing auditor for extracted balance sheets, income statements, and cash flow reports.

Geometric spatial relationship grounding evaluator verifying relative positional assertions between objects and UI controls

Ebbinghaus forgetting curve auditor calculating retention probabilities and executing garbage collection

Set-of-Marks (SoM) bounding box resolution and relative viewport coordinate mapper for computer-use vision agents

Continual few-shot exemplar distiller mining high-scoring execution trajectories into prompt demonstrations

Full-duplex conversational barge-in arbitrator classifying user interruptions, backchannels, and acoustic echo with context rollback.

End-to-end conversational voice agent latency telemetry profiler tracking VAD, STT, LLM-TTFT, TTS-TTFB, and playout bottlenecks.

Egress data exfiltration firewall detecting obfuscated credentials, private keys, and API tokens in payloads

Multimodal chart coordinate calibration and tabular dataset recovery engine transforming visual bar, line, and scatter charts into structured numbers.

Indirect prompt injection sanitizer and delimiter boundary firewall neutralizing embedded command overrides

Role-based access control and tool privilege attenuator preventing unauthorized tool invocations

Real-time acoustic VAD & semantic turn-completion endpoint detector distinguishing mid-sentence hesitation pauses from finished speech turns.

Two-tier memory consolidation engine distilling ephemeral working memory into persistent episodic knowledge

Set-of-Marks (SoM) bounding box resolution and relative viewport coordinate mapper for computer-use vision agents

Multi-frame GUI computer-use action trajectory summarizer detecting dead clicks and UI rendering latency stalls

Browser DOM accessibility tree pruner filtering non-interactive noise and generating dense actionable trees for web agents

Multimodal visual hallucination verifier cross-checking vision model claims against ground-truth OCR and bounding box metadata

Hierarchical semantic chunk re-ranker evaluating hybrid keyword and dense relevance scores for agentic RAG

Adaptive WebRTC audio packet jitter buffer and packet loss concealment (PLC) engine maintaining smooth voice playout over volatile network streams.

Low-latency streaming prosody, SSML, and emotion pacing modulator dynamically tailoring speech pitch, cadence, and pause inflections.

Contract cross-reference resolver and defined-term graph analyzer detecting circular references and substituting statutory definitions.

Multi-frame GUI computer-use action trajectory summarizer detecting dead clicks and UI rendering latency stalls

Deterministic 2D bounding-box spatial clustering and table reconstruction engine recovering multi-column layouts, merged headers, and grid hierarchies.

Browser DOM accessibility tree pruner filtering non-interactive noise and generating dense actionable trees for web agents

Low-latency streaming prosody, SSML, and emotion pacing modulator dynamically tailoring speech pitch, cadence, and pause inflections.

Packet ordering simulation and inter-arrival jitter telemetry.

Deterministic 2D bounding-box spatial clustering and table reconstruction engine recovering multi-column layouts, merged headers, and grid hierarchies.

Dynamic honeypot and cryptographic canary token sentinel detecting prompt extraction and triggering session freezes

Role-based access control and tool privilege attenuator preventing unauthorized tool invocations

Geometric spatial relationship grounding evaluator verifying relative positional assertions between objects and UI controls

Full-duplex conversational barge-in arbitrator classifying user interruptions, backchannels, and acoustic echo with context rollback.

End-to-end conversational voice agent latency telemetry profiler tracking VAD, STT, LLM-TTFT, TTS-TTFB, and playout bottlenecks.

Egress data exfiltration firewall detecting obfuscated credentials, private keys, and API tokens in payloads

Hierarchical semantic chunk re-ranker evaluating hybrid keyword and dense relevance scores for agentic RAG

Multimodal visual hallucination verifier cross-checking vision model claims against ground-truth OCR and bounding box metadata

Multimodal chart coordinate calibration and tabular dataset recovery engine transforming visual bar, line, and scatter charts into structured numbers.

Contract cross-reference resolver and defined-term graph analyzer detecting circular references and substituting statutory definitions.

Dynamic honeypot and cryptographic canary token sentinel detecting prompt extraction and triggering session freezes

Cross-platform personal episodic memory and context graph synthesizer compiling recency-decayed briefings for interactions

Native Model Context Protocol (MCP) server exposing HubX's mobile-first multimodal toolchain: vision diagnostics, voice transcription, photo-realistic generation, and spatial design.

Native Model Context Protocol (MCP) server exposing HubX's mobile-first multimodal toolchain: vision diagnostics, voice transcription, photo-realistic generation, and spatial design.

Native Model Context Protocol (MCP) server providing typed state-action schema arbitration, deterministic action dispatch, and token-saving pre-escalation filters.

Native Model Context Protocol (MCP) server fusing Meta ambient multimodal perception with Muse continuous episodic memory streams and Ebbinghaus recency decay.

Native Model Context Protocol (MCP) server providing typed state-action schema arbitration, deterministic action dispatch, and token-saving pre-escalation filters.

Native Model Context Protocol (MCP) server fusing Meta ambient multimodal perception with Muse continuous episodic memory streams and Ebbinghaus recency decay.

Personal digital asset decluttering agent classifying orphaned downloads, duplicate screenshots, and stale browser bookmarks.

Multi-strategy anomaly detector computing standard Z-score, modified median absolute deviation (MAD), and Tukey IQR fences on numerical streams.

Token-safe AST import re-aliasing and dependency migration engine safely replacing module paths and callsites without regex bugs.

Entity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.

Zero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.

Personal inbox cognitive triage engine classifying actionability, effort duration, and urgency to prevent attention fragmentation.

Token-safe AST import re-aliasing and dependency migration engine safely replacing module paths and callsites without regex bugs.

Cryptographic double-entry bookkeeping engine enforcing sum(Debits) == sum(Credits) invariants and hash-chained audit trails.

Context window attention optimizer reordering retrieved documents to place critical evidence at prompt boundaries, mitigating lost-in-the-middle degradation.

Trajectory state entropy and cyclic repetition detector identifying autonomous agent infinite tool loops and planning deadlocks.

High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.

Autonomous web form inspector and schema auto-mapper matching input attributes, autocomplete hints, and regex validations to agent state.

GenPark AI Agent Skill - Multimodal ambient visual anchoring connecting physical AI Gadgets with digital Services inspired by Meta Ray-Ban / Muse.

Autonomous web form inspector and schema auto-mapper matching input attributes, autocomplete hints, and regex validations to agent state.

Cognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.

High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.

AST-level static call-graph analyzer and dead code pruner identifying orphaned functions, unreachable methods, and token-bloat clusters.

Real-time transaction velocity profiler and fraud sentinel detecting card-testing clusters, abnormal volume spikes, and account takeovers.

Multi-vector heuristic prompt injection and jailbreak detector analyzing system overrides, delimiter breakouts, and base64 payload evasion.

Anti-fragile habit tracker and elastic degradation engine preventing streak-break abandonment through adaptive micro-fallbacks.

Instinct AI-inspired zero-prompt proactive personal agent detecting user attention cues, computing intent probabilities, and executing guarded dry-run actions.

Cognitive multi-tier memory kernel managing working scratchpad, sliding dialogue buffer, and episodic memories with exponential recency decay.

Zero-dependency Markdown table to structured JSON transformer with automated column type inference and format normalization.

Execution trajectory evaluator computing action-level precision, recall, and Levenshtein sequence edit distance against gold benchmarks.

Anti-fragile habit tracker and elastic degradation engine preventing streak-break abandonment through adaptive micro-fallbacks.

Zero-dependency HTML DOM semantic tree pruner compressing web markup into accessibility-friendly clean trees with 80%+ token reduction.

Multi-strategy anomaly detector computing standard Z-score, modified median absolute deviation (MAD), and Tukey IQR fences on numerical streams.

Execution trajectory evaluator computing action-level precision, recall, and Levenshtein sequence edit distance against gold benchmarks.

Semantic versioning (SemVer 2.0) breaking change auditor inspecting AST public API surface diffs, parameter reordering, and removed exports.

Personal digital asset decluttering agent classifying orphaned downloads, duplicate screenshots, and stale browser bookmarks.

Master dual-process cognitive orchestrator uniting Meta ambient perception, Muse episodic memory, Instinct proactive agency, and Jev System-1 decision routing.

Zero-dependency AST & heuristic bash command sandbox guard blocking destructive system mutations, path traversals, and reverse shells.

Zero-dependency Holt linear exponential smoothing engine forecasting numerical trends with multi-step horizon and variance confidence bands.

AST McCabe cyclomatic complexity and cognitive nesting depth evaluator identifying refactoring hotspots and decomposition plans.

Web URL canonicalization and anti-crawler trap detector identifying circular paths, infinite paginations, and tracking parameter bloat.

GenPark AI Agent Skill - Safe micro-action delegation with user guardrails and token budget gating inspired by Instinct.

Categorized index of 718 public GenPark AI agent skills, with tested Python packages and MCP integrations.

Jev-inspired System-1 subconscious cognitive decision layer resolving typed routing, loop-stall arbitration, and tool safety checks at sub-millisecond latency.

Context window attention optimizer reordering retrieved documents to place critical evidence at prompt boundaries, mitigating lost-in-the-middle degradation.

Zero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.

Jev-inspired System-1 subconscious cognitive decision layer resolving typed routing, loop-stall arbitration, and tool safety checks at sub-millisecond latency.

Two-sample Welch's t-test hypothesis evaluator computing Satterthwaite degrees of freedom and two-tailed p-values for A/B testing.

Differential privacy epsilon-noise generator and quasi-identifier redaction kernel protecting tabular data releases from re-identification.

Master dual-process cognitive orchestrator uniting Meta ambient perception, Muse episodic memory, Instinct proactive agency, and Jev System-1 decision routing.

Trajectory state entropy and cyclic repetition detector identifying autonomous agent infinite tool loops and planning deadlocks.

Entity-relation-object triplet extractor and multi-hop path reasoning kernel with Cypher and JSON-LD graph generation.

Chronotype-aligned circadian sleep architecture calculator optimizing 90-minute ultradian cycles, caffeine cutoffs, and light exposure.

Atomic claim decomposition and cross-context fact verification engine detecting ungrounded claims, numerical contradictions, and hallucinated entities against reference knowledge.

Atomic claim decomposition and cross-context fact verification engine detecting ungrounded claims, numerical contradictions, and hallucinated entities against reference knowledge.

Instant zero-LLM deterministic JSON extractor & schema auto-repair engine healing truncated braces, markdown wrappers & invalid types.

Production-grade hybrid sparse-dense memory retrieval engine combining BM25 keyword search, semantic n-gram cosine similarity, and recency decay ranking for agent episodic long-term memory.

Master cognitive personal copilot integrating Today AI (agenda), Manus (autonomous sandbox), Cue (ambient cues), Instinct (fast reflex), and Muse (episodic memory).

Dynamic few-shot in-context exemplar selector utilizing semantic token overlap, cosine similarity and Maximal Marginal Relevance (MMR) diversity ranking for prompt optimization.

Topological tool dependency DAG scheduler and speculative prefetcher resolving agent tool execution graphs with parallel batching and speculative argument evaluation.

Ambient desktop context listener, screen text & clipboard change trigger, and non-intrusive proactive intent predictor (inspired by Cue).

Multi-file AST dependency graph parser & minimum context slicer extracting symbol call-trees for coding agents.

Topological tool dependency DAG scheduler and speculative prefetcher resolving agent tool execution graphs with parallel batching and speculative argument evaluation.

Instinct AI-inspired zero-prompt proactive personal agent detecting user attention cues, computing intent probabilities, and executing guarded dry-run actions.

Multivariate linear regression engine computing MSE loss, analytical gradient descent weights, and R-squared coefficient of determination.

Real-time transaction velocity profiler and fraud sentinel detecting card-testing clusters, abnormal volume spikes, and account takeovers.

Deterministic sandboxed virtual code execution engine and AST security analyzer verifying multi-language agent code, blocking dangerous syscalls, and capturing isolated execution telemetry.

Ambient desktop context listener, screen text & clipboard change trigger, and non-intrusive proactive intent predictor (inspired by Cue).

Heuristic and pattern-based agent prompt injection sanitizer and LLM jailbreak firewall detecting adversarial jailbreaks, system prompt exfiltration, and tool hijacking.

Dynamic long-horizon context window compression engine pruning verbose tool outputs, HTML boilerplate & semantic redundancy by 40-70%.

Multimodal sensory grounding (Meta Ray-Ban audio/vision) integrated with long-term episodic life memory graphs and empathetic emotional resonance (Muse).

Dynamic long-horizon context window compression engine pruning verbose tool outputs, HTML boilerplate & semantic redundancy by 40-70%.

Instant zero-LLM deterministic JSON extractor & schema auto-repair engine healing truncated braces, markdown wrappers & invalid types.

Human-in-the-Loop policy gatekeeper enforcing risk tiers, reversible checkpoints & token approval bounds for autonomous agents.

General-purpose autonomous task decomposition, multi-modal web/sandbox execution loop, and self-correcting goal resolution (inspired by Manus AI).

Multi-modal speech prosody and vocal sentiment analyzer detecting speech rate, pitch variance, and user cognitive fatigue to dynamically calibrate agent response pacing.

Multi-agent recursive self-critique and reflection engine executing iterative evaluation-revision loops to autonomously repair logic defects, test failures, and hallucinations.

Dynamic Cognitive Load, Latency & Token Budget Router. Monitors running agent loops, estimates token consumption and monetary cost, prunes verbose thinking chains when nearing limits, and routes sub-t

Multi-modal speech prosody and vocal sentiment analyzer detecting speech rate, pitch variance, and user cognitive fatigue to dynamically calibrate agent response pacing.

Proactive High-Stakes Intent Disambiguator & Option Clarifier. Detects under-specified user goals, assesses reversibility and risk, and constructs minimal multiple-choice clarifications before trigger

Heuristic and pattern-based agent prompt injection sanitizer and LLM jailbreak firewall detecting adversarial jailbreaks, system prompt exfiltration, and tool hijacking.

Proactive daily agenda and cognitive briefing synthesizer for personal agents (inspired by Today.ai), orchestrating circadian energy focus blocks, asynchronous task triage, and meeting prep.

Heuristic multi-column document and tabular markdown extractor converting ASCII/OCR text dumps, aligned spacing, and CSV/TSV into clean GitHub Flavored Markdown and typed JSON.

GenPark AI Agent Skill - Zero-prompt proactive intent anticipation, activity & cursor context sensing inspired by Instinct.

Multi-vector heuristic prompt injection and jailbreak detector analyzing system overrides, delimiter breakouts, and base64 payload evasion.

GenPark AI Agent Skill - Continuous hierarchical episodic memory stream, preference decay, contextual memory anchor inspired by Meta Muse.

Biological Sleep-Cycle & Ebbinghaus Forgetting Curve Episodic-to-Semantic Memory Consolidation Engine. Decays stale transient interactions and consolidates frequent episodic events into enduring seman

Local-first zero-knowledge personal vault encryptor and PII sanitizer masking credentials, credit cards, and addresses before cloud LLM dispatch with client-side rehydration.

Multi-Agent Divergence-Convergence Debate Engine (MAD / Society of Mind). Coordinates multiple specialized personas to debate high-stakes decisions and aggregate into an explainable consensus with dis

Deterministic sandboxed virtual code execution engine and AST security analyzer verifying multi-language agent code, blocking dangerous syscalls, and capturing isolated execution telemetry.

Proactive High-Stakes Intent Disambiguator & Option Clarifier. Detects under-specified user goals, assesses reversibility and risk, and constructs minimal multiple-choice clarifications before trigger

GenPark AI Agent Skill - Milwaukee Tool M18 FUEL with ONE-KEY smart cordless hardware, BLE proximity tracking, torque calibration & jobsite lockout.

Behavioral personal spending impulse guard enforcing cooling-off friction timers and net work-hour wage conversions.

Personal inbox cognitive triage engine classifying actionability, effort duration, and urgency to prevent attention fragmentation.

Monorepo dependency cycle resolver and topological build-order planner using Tarjan SCC and Kahn algorithms.

Zero-dependency Holt linear exponential smoothing engine forecasting numerical trends with multi-step horizon and variance confidence bands.

Zero-dependency AST & heuristic bash command sandbox guard blocking destructive system mutations, path traversals, and reverse shells.

Intelligent payment recovery and smart dunning strategist optimizing decline-code retry windows and involuntary churn mitigation.

Differential privacy epsilon-noise generator and quasi-identifier redaction kernel protecting tabular data releases from re-identification.

Personal knowledge vault graph compiler and bi-directional link indexer parsing [[wikilinks]], tags, and unlinked mentions across personal notes (inspired by Obsidian and Roam).

Multi-agent recursive self-critique and reflection engine executing iterative evaluation-revision loops to autonomously repair logic defects, test failures, and hallucinations.

Autonomous Agent Tree-of-Thoughts (ToT) State Rollback Checkpointer. Allows long-running personal agents (Manus, Devin) to snapshot environment/context states, evaluate branch viability, and backtrack

Multi-Agent Divergence-Convergence Debate Engine (MAD / Society of Mind). Coordinates multiple specialized personas to debate high-stakes decisions and aggregate into an explainable consensus with dis

Autonomous personal communication and email triage sentinel performing multi-factor urgency scoring, VIP filtering, and context-aware executive auto-drafting.

Biological Sleep-Cycle & Ebbinghaus Forgetting Curve Episodic-to-Semantic Memory Consolidation Engine. Decays stale transient interactions and consolidates frequent episodic events into enduring seman

Personal knowledge vault graph compiler and bi-directional link indexer parsing [[wikilinks]], tags, and unlinked mentions across personal notes (inspired by Obsidian and Roam).

Autonomous Agent Tree-of-Thoughts (ToT) State Rollback Checkpointer. Allows long-running personal agents (Manus, Devin) to snapshot environment/context states, evaluate branch viability, and backtrack

Local-first zero-knowledge personal vault encryptor and PII sanitizer masking credentials, credit cards, and addresses before cloud LLM dispatch with client-side rehydration.

Dynamic Cognitive Load, Latency & Token Budget Router. Monitors running agent loops, estimates token consumption and monetary cost, prunes verbose thinking chains when nearing limits, and routes sub-t

Autonomous personal communication and email triage sentinel performing multi-factor urgency scoring, VIP filtering, and context-aware executive auto-drafting.

Heuristic multi-column document and tabular markdown extractor converting ASCII/OCR text dumps, aligned spacing, and CSV/TSV into clean GitHub Flavored Markdown and typed JSON.

Master cognitive personal copilot integrating Today AI (agenda), Manus (autonomous sandbox), Cue (ambient cues), Instinct (fast reflex), and Muse (episodic memory).

Proactive daily agenda and cognitive briefing synthesizer for personal agents (inspired by Today.ai), orchestrating circadian energy focus blocks, asynchronous task triage, and meeting prep.

Dynamic few-shot in-context exemplar selector utilizing semantic token overlap, cosine similarity and Maximal Marginal Relevance (MMR) diversity ranking for prompt optimization.

Multimodal sensory grounding (Meta Ray-Ban audio/vision) integrated with long-term episodic life memory graphs and empathetic emotional resonance (Muse).

Multi-provider token-bucket and sliding-window rate limiter preventing TPM/RPM throttling across LLM APIs with predictive token consumption budgeting.

General-purpose autonomous task decomposition, multi-modal web/sandbox execution loop, and self-correcting goal resolution (inspired by Manus AI).

Multi-provider token-bucket and sliding-window rate limiter preventing TPM/RPM throttling across LLM APIs with predictive token consumption budgeting.

Production-grade Model Context Protocol (MCP) server for Bale Messenger with 32 tools for LLMs (Claude, Cursor, Antigravity) to interact with user accounts.

inertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.

麦当劳 MCP 没给「口味」这个维度，我给 119 款餐品手工标了一份（每款附配料依据、54% 可溯源至官方公示文件）。说「想吃甜的、要酥脆的、不要牛肉」就能找餐品，顺手把营养和优惠券算到最省。零 Token 打开即玩。

Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-fil

WorkForge is a Windows MCP gateway that lets ChatGPT inspect files, resume Git work, make SHA-guarded edits, read images, and run supervised PowerShell jobs.

Ad automation MCP server: generate ad creative and launch Meta campaigns from Claude or any AI agent. Hosted at https://pixero.ai/api/mcp

西门子博途(博图) / Siemens TIA Portal V16–V21 AI 编程智能体。支持 S7-1200/1500 SCL 代码自动生成、编译诊断、工程归档(.zap)、PLCSIM 仿真与 PLC 下载。| AI agent for Siemens TIA Portal (S7-1200/1500): SCL code generation, compile diagnostics,

MCP server and desktop app for editing Excel - faster, and more efficient

Персональный агент для вашей 1С — WhatsApp и MCP. Open-source расширение 1С (bilem.cfe) и MCP-сервер для Claude, ChatGPT, Cursor, OpenClaw, Hermes. 🇰🇿 Kazakhstan

Skills that let Claude Code, GitHub Copilot, Cursor, Kiro and other coding agents work with OutSystems 11 apps via the Service Studio MCP server.

看看哪些麦当劳权益快到期，哪些值得用，哪些不用为了到期硬消费。基于麦当劳官方 MCP 的 WorkBuddy Skill：只读查询优惠券与积分，按预算给出最多两套经官方接口试算的用餐方案。McDonald's coupon & points expiry assistant — a WorkBuddy Skill on the official McDonald's MCP. Read-only

AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.

Multi-account Gmail MCP server on Cloudflare Workers — one deployment, one Google sign-in per connection, any MCP client

🔥 AI 求职雷达｜一句话同时搜 BOSS直聘 + 猎聘，找到匹配你简历的岗位。

PickleShell ChatGPT Plugin - Interactive sessions with your local AI agent from ChatGPT

Prices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MC

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green

Personal recurring subscription auditor identifying dormant zombie services and recovering recurring annual spend

基于麦当劳官方 mcd-mcp-server 的 MCP 客户端与 WorkBuddy 技能：扫描历史订单中仍来得及用餐评价的权益机会，盘点积分兑换，聚合当月活动。

Pulse — Hermes-style self-improving AI agent. Reliability-first rebuild with evaluated skill self-evolution, multi-agent team orchestration, dialectic user modeling, and fully self-hosted default stac

An auditable local workspace for Pi: pinned upstream source, curated extensions, bounded MCP tooling, and a reproducible external runtime.

Local AI assistant for the Axelera Voyager SDK and Metis AIPU — semantic RAG over the public Axelera sources + workflow skills, via MCP. No account, no cloud.

A real local terminal in Edge/Chrome that gives Codex, Claude Code, Kimi Code, and any MCP CLI 41 local MCP tools through Browser Core v2.

DJAI Academy community-built, free open-source technical SEO crawler and Screaming Frog alternative with JavaScript audits, reports, a local dashboard, and an MCP server for AI agents. Theoretical 100

A modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.

DeepDepCat — all-in-one AI desktop workbench: Code assistant + Depwork office automation. Homepage & releases. WPS Office MCP server included (open source).

MCP channel server for the Zalo Bot API. Talk to your Claude Code session from Zalo, with pairing, allowlists, and group gating.

Local-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.

A local browser your coding agent can actually finish a job in — file uploads, cross-origin iframes, native dialogs, and downloads, all via CLI/MCP.

Give Claude hands in your own browser — a Chrome extension + MCP server that lets Claude Code drive your real, logged-in Chrome with human-shaped clicks, drags and keystrokes.

Standalone Agent Client Protocol (ACP) server for DeepSeek Harness with real-time streaming, reasoning trace, MCP tools, and session recovery.

Multi-agent browser MCP runtime for isolated, persistent, parallel Playwright sessions. Run multiple AI agents without shared tabs or browser state.

Hardware-adaptive local LLM & cloud cascading gateway. Sub-5ms intelligent routing, 3-token lookahead failover, asymmetric verification, 1-click IDE config, and MCP for $0 token cost.

⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel, Target Memory & Deterministic Automation.

Spring AI vs LangChain4j vs SAA 三框架同台对比（配套篇2）

Capture browser API traffic via CDP and turn any site into a ready-to-run FastMCP server, with no official API required.

Multiplayer browser sessions for developers and AI coding agents

A lightweight, sub-millisecond security shim that prevents AI agents from accessing sensitive files (.env, SSH keys) and executing destructive commands via MCP.

麦门抽签 - 麦当劳运势抽签式点餐 Skill | McDonalds Fortune-Telling Ordering

麦门卡路里精算师 - 基于麦当劳 MCP 真实营养数据的热量约束配餐Skill

MagicTeX — a LaTeX editor for AI agents (Claude Code): live PDF preview, PDF comments that drive edits, Visual (WYSIWYG) mode, and git-tracked history. No local TeX install.

Talk to your cloud — an open-source AI agent that reads your code, operates AWS & GCP, and opens PRs. Self-hostable.

Native C++17 AI agent runtime — local-first, embeddable, MCP-native. Tool-calling, memory, and an async agent loop that runs where Python can't: ROS2, game threads, drones, HFT.

Self-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.

AEP: Agent Event Protocol — open async event layer for agents, tools, memory, and multi-agent runtimes. 4-language reference with cross-language conformance.

Open-source AI Strength & Conditioning coach for your terminal. Runs in Claude Code / Gemini CLI / Codex — the LLM narrates, a deterministic engine calculates, and it won't lie about unrealistic goals

Connect any AI agent to your personal Telegram via the official Business API — no userbot, no ban risk, no Premium. Agent reads & searches full history, drafts replies; every reply waits for your ✅. M

Lightweight self-hosted CRM with a built-in MCP connector. Let Claude, ChatGPT, or Gemini run your pipeline.

Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). Apach

A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.

The OKF-go provides a high-performance suite of utilities to validate bundles, harvest metadata from databases and APIs, assemble context for Large Language Models (LLMs), and run an MCP Server.

Unofficial Cloudflare DNS/email-auth MCP server for AI agents: DMARC, SPF, BIMI, Email Routing, Wrangler, safe DNS fixes.

Code-enforced incident-response agent that investigates SigNoz alerts, publishes evidence-backed root-cause claims, and gates every action behind a safety policy. Built for Agents of SigNoz hackathon.

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, i

Chartbrew + AI agents. MCP server exposing Chartbrew's documented API: teams, connections, datasets, dashboards, charts, live queries, and secure embedding. TypeScript · stdio · restricted/unrestricte

Drive Unreal Engine 5 from an AI agent — MCP server over the Remote Control API and in-editor Python. No C++ plugin to compile.

OmniSignal.ai – Live market intelligence & AI content strategy: trends, competitor moves, content calendar.

MCP server for searching your local OpenCode conversation history

MCP server for Lufa Farms grocery shopping — browse the marketplace, manage your basket, and check orders through natural language

MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.

AI-native terminal & SSH client — built-in DeepSeek Harness to launch agents in TUI or embedded Web UI, plus SFTP, serial/Telnet and MCP server.

WordPress MCP server for Claude, Cursor, Codex and Copilot. 103 typed abilities in the free plugin: posts, pages, Gutenberg blocks, media, menus, taxonomies, plugins and themes, with OAuth 2.1, safety

Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.

Executable AI agent readiness gate: GitHub Action, prompt injection evals, LangGraph traces, risk profiles, and bilingual EN/中文 docs.

Lightweight browser-side AI agent framework for legacy enterprise web apps—Java 8, Spring Boot 2, TypeScript, MCP/WebMCP, OpenAI-compatible LLMs, tool calling, streaming, audit, and persistence. 面向存量企

为了服务于大众

Local-first AI brain for personal relationships and communication, powered by MCP｜多平台身份图谱、关系记忆、回复策略与受控自动回复

Identity and reputation for AI agents: resolve social handles to wallet addresses, check reputation scores, and send tokens from any MCP client.

Production-grade, token-optimized FastMCP SQLite Server with sub-millisecond O(1) schema discovery, opcode execution watchdog, and fuzzy self-healing.

像塑 MCP | AI Agent scene editing, scripting and playtesting for Douyin Xiangsu 9.4. Effect House compatibility unverified.

Give an AI agent full remote control of a Windows PC - with zero console windows flashing on screen. 让 AI 完全操控你的 Windows 电脑，屏幕上不闪任何黑窗口。

Let Claude code, chatgpt codex or control your own Chrome. Chrome extension + MCP server: Jev, TypeSafe's decision model, picks each click in ~0.5 s for a fraction of a cent. MIT, bring your own OpenR

Local MCP bridge that lets an AI assistant help build tabletop battle maps from assets you already own.

跨平台 SSH 终端。用户在本机登录后，Agent 通过 MCP 继续操作同一条会话。你的终端，助手可以接着用。

AM Code — agentic coding assistant (VS Code + Windows/Linux/macOS desktop) with your own models, MCP support and a token saver that compresses every request. | دستیار کدنویسی ایجنت با مدل‌های خودت

MCP server that lets Claude and other AI assistants build, animate, preview and render motion graphics in a live Adobe After Effects project: 77 tools for comps, layers, keyframes, springs, text revea

Reliability-focused Xiaohongshu MCP: async writes, idempotency, durable recovery, and verified comment replies.

麦门圆桌（mcd-roundtable）｜五个 AI 人格辩论，逼出最优麦当劳订单。基于麦当劳 MCP（mcd-mcp / Model Context Protocol）的多智能体点餐决策 Skill：菜单、券、营养、价格全部来自官方接口，金额只认 calculate-price，绝不估算。凑单最省 / 优惠券最大化 / 营养配餐 / 一键下单。Multi-agent McDonald's MCP

MealPR — Code Review for Your Meal. Turns McDonald's MCP ordering into a reviewable, human-approved agent workflow.

麦麦点餐最优解｜WorkBuddy Skill + 麦当劳 MCP + 本地 Python 组合求解。按预算、热量和蛋白质筛选搭配，附无需 MCP Token 的离线演示。

Connect AI models to your own computer and MCP tools — with device-side control.

通勤路上的麦当劳点单管家｜基于麦当劳 MCP：按到达时段过滤餐品、按到期紧迫度调度优惠券，输出可直接执行的预约订单方案

MCP stdio server that lets Claude Code drive your real Chrome window (your logins, your cookies, zero API keys) via a Chrome MV3 extension.