MCP servers for developer-tools

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zer

Your agents already solved this. deja finds it — retroactive search and MCP recall over the session logs your coding agents already wrote. Cross-agent, SSH-portable, one zero-dep binary, fully local.

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens in our benchmarks. Every change is record

Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.

The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

Local search across your files, git repos and AI agent sessions on your Mac. An MCP server gives your agents the best context, a 3D map shows your work by topic, and git blame shows who knows what.

⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.

Your feedback layer for AI collaboration. Point at anything on your Mac - text, screenshots, web elements, or voice - and your agent reads and resolves your comments over MCP.

Annotate a running iOS simulator in your browser, and hand the notes to your coding agent.

See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read from the output, faked passes caught, Claude Code sent back

Let ChatGPT use Codex's local toolbox, then call Codex only when needed.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Android emulator & ADB GUI for Mac: dark mode, font size, RTL, TalkBack, network, GPS, Layout Inspector in dp. Built-in MCP server lets Claude Code, Codex and Cursor drive the emulator.

Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks.

Codex plugin: choose which past images go to the model with your next message. Unchecked images become placeholders, the task goes on, and requests stay small.

Give ChatGPT a real terminal on your Mac. Open-source MCP bridge for shell, files, PTY sessions, jobs, and Codex history.

Anti-hallucination gate for AI coding agents — 8 MCP tools catch invented APIs (17 languages), fake "all tests pass" claims, and slopsquatting packages before they ship. Zero-dependency Agent Plugins

Kether-governed AI agent orchestration with Pi/MCP, isolated workers, LSP tools, and a portable Windows/WSL2 installer

Tested MCP server, MCPB, Docker, and OpenAPI for annotated post-trade candlestick charts from broker or exchange fills.

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

Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.

Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claude Code plugin and an MCP server.

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

面向可信个人开发机的 MCP 编程运行时：Agent Transport、Windows Workbench、证据优先的项目连续性 | Personal-workstation MCP coding runtime

Compile an API, an MCP server, a database or a web page into a CLI your agent can run. Ten engines, one output contract, 4.1x less context than raw MCP.

16 reusable skills and 6 agents for Codex, Claude Code, Cursor, OpenCode and Grok Bot: Humanizer, ML debugging, PR review and Skill Watch.

Lighthouse-style audits for AI-agent readiness, LLM crawlers, MCP clients, and the agentic web

Cross-agent coordination for AI coding agents. One daemon, one database — so multiple agents in one repo can see each other's plan, tasks, and file claims.

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

A shared to-do list for you and your AI coding agents

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down.

MCP server: turn narrated screen recordings into agent-ready data — local Whisper transcript, scene keyframes, OCR, wall-clock anchoring. Record your screen, talk — your AI agent files the bugs.

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

ChatGPT <-> Codex bridge: local coding agents ask ChatGPT for advice, and ChatGPT can inspect or steer your running Codex sessions. No API key.

Gives AI coding agents exactly the code they need instead of whole files. Semantic code graph, impact analysis, and MCP server in one static Rust binary.

Angular DevTools : inspect components, signals, DI, and routes. Runs as a Chrome extension, embedded panel, standalone CLI, static report, or MCP server for coding agents. Built with Devframe.

Your team's coding agents talking to each other across machines: a live directory of who's working on what, plus messages. Peer to peer, no server.

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

改配置+重启才能加 MCP？DeepSeek Harness (DSH) 插件「技能配置」解决：设置页粘贴 JSON 即连 MCP 服务器、热加载免重启；上传 zip/.skill 自动识别 SKILL.md，创建/编辑/启停技能，即点即用

A cross-platform desktop app for doing local code reviews of your own git repositories. Single user, single machine, no server, no account.

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

Local CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.

Local-first MCP server: give ChatGPT & friends grounded, current context on the repos your coding agents work in. Live git, docs, tasks, agent handoffs.

Local-first, MCP-native tool for modelling software architecture. C4-style semantic model, React Flow editor, SQLite, single container — a self-hosted Structurizr alternative your AI client can edit o

MCP server that gives your AI coding agent a map of your polyglot codebase — reverse dependencies, gRPC tracing, event/topic flows, and doc search, without burning context. Single local Rust binary, n

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

Zero-dependency CLI to scan, recommend, deduplicate, audit, and visualize Claude Code / Codex skills and MCP servers.

A Model Context Protocol server for persistent project-specific AI agent context.

MCP server and design skill that grounds coding-agent UI work in real product screens. Two tools, npx-installable.

Enterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-tier AI providers.

Engineering MCP is a repository-aware AI engineering control plane for orchestrating trusted coding workers through MCP, with lifecycle management, execution isolation, and verifiable task handoff.

A Claude Code plugin that checks every file and shell call an AI agent makes, fixes what it safely can, and tells the agent how to fix the rest. Windows and macOS.

Local, read-only MCP server and CLI that gives AI coding assistants a commit-pinned map of your codebase.

Aixle Flow — orchestrate coding agents through durable, inspectable workflows.

A macOS window manager with snap zones you draw yourself and workspaces that reopen your apps on the right monitor — plus on-device OCR, keep-awake, screenshot annotation, pointer tools, a shortcut gu

Cross-repository context for coding agents. A local-first MCP server that turns finished sessions into findings with commit provenance and staleness checks.

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

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

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

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

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

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.

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.

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.

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

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%.

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.

RFC-compliant Server-Sent Events (SSE) streaming frame parser handling data, events, ids, and multi-line payloads

RFC-compliant Server-Sent Events (SSE) streaming frame parser handling data, events, ids, and multi-line payloads

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

Universal Cross-Platform Commerce Inventory & Price Arbitrage Engine (inspired by Meta Muse, Shopify, Walmart, Instacart). Performs real-time multi-merchant price comparison, coupon stacking, delivery

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

Enterprise Work Agent Goal-to-Artifact DAG Pipeline (inspired by WorkBuddy, Tencent Docs, WeChat Work Multi-Agent). Decomposes high-level business objectives into topological sub-tasks and directly sy

Universal Agentic Travel & Multi-Leg Hospitality Itinerary Synthesizer (inspired by Meta Muse, Expedia, Booking). Translates natural language vacation and business travel goals into multi-leg flight s

Enterprise Knowledge Graph Provenance & Anti-Hallucination Tracer (inspired by Tencent Docs, Meeting & Enterprise Knowledge Bases). Provides cryptographic chunk hashing, reverse claim-to-source attrib

Cryptographic Delegated Agentic Commerce Escrow & Settlement Ledger (inspired by Mastercard Agent Connect & Stripe Split-Settlements). Provides multi-party conditional escrow locking, autonomous proof

Universal Agentic Commerce Multi-Merchant Cart & Checkout Engine (inspired by Meta Muse, Shopify, Instacart, Walmart, Expedia). Translates consumer intent into aggregated item discovery, cross-merchan

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

Cryptographic Agent Delegated Payment Authorization & Tokenized Checkout Sentinel (inspired by Mastercard Agent Connect, Stripe Agent Delegation, Visa Virtual Cards). Enforces spend limits, velocity t

Enterprise Private Context & Role-Based Access Control (RBAC) Governance Sentinel (inspired by WeChat Work, Tencent Docs enterprise permissions). Inspects ingested context, classifies security clearan

Enterprise Managed Agent Fleet Lifecycle Supervisor (inspired by Tencent WorkBuddy & Anthropic Managed Agents). Orchestrates worker agent registration, capability-based task dispatch, continuous heart

Universal Agentic Commerce Multi-Merchant Cart & Checkout Engine (inspired by Meta Muse, Shopify, Instacart, Walmart, Expedia). Translates consumer intent into aggregated item discovery, cross-merchan

Enterprise Presentation & Slide Deck Narrative Structure Compiler (inspired by Tencent WorkBuddy Goal-to-PPT Workflows). Transforms raw enterprise documents, meeting transcripts, and KPI metrics into

Universal Agentic Travel & Multi-Leg Hospitality Itinerary Synthesizer (inspired by Meta Muse, Expedia, Booking). Translates natural language vacation and business travel goals into multi-leg flight s

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

Universal Cross-Platform Commerce Inventory & Price Arbitrage Engine (inspired by Meta Muse, Shopify, Walmart, Instacart). Performs real-time multi-merchant price comparison, coupon stacking, delivery

Enterprise Spreadsheet Financial Model & Formula DAG Synthesizer (inspired by Tencent WorkBuddy Goal-to-Excel Workflows). Synthesizes multi-tab financial models, detects circular references, compiles

Enterprise Spreadsheet Financial Model & Formula DAG Synthesizer (inspired by Tencent WorkBuddy Goal-to-Excel Workflows). Synthesizes multi-tab financial models, detects circular references, compiles

Cryptographic Agent Delegated Payment Authorization & Tokenized Checkout Sentinel (inspired by Mastercard Agent Connect, Stripe Agent Delegation, Visa Virtual Cards). Enforces spend limits, velocity t

Sponsored Agent Intent Auction & Privacy-Preserving Ad Monetization Router (inspired by Sponsored Agents, Meta AI Ad Platform). Runs second-price Vickrey auctions matching consumer query intent with b

Model Context Protocol (MCP) JSON-RPC 2.0 proxy router with capability negotiation and dynamic tool dispatch

Autonomous Agentic Recurring Subscription Governance & Price Hike Autopilot (inspired by Stripe Billing, Mastercard Agent Connect recurring mandates, and SaaS spend optimizers). Detects recurring char

Real-time Multimodal Spatial Audio-Visual Grounding Engine (inspired by Meta Ray-Ban & Meta Muse). Fuses 2D/3D visual bounding boxes, user head-pose gaze vectors, and acoustic beamforming azimuth angl

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

Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable info

Autonomous Agentic Post-Purchase Tracking & Delivery Dispute Arbiter (inspired by Meta Muse, Shopify, Walmart, Instacart Post-Checkout Operations). Ingests carrier webhook events, tracks transit anoma

Enterprise Executive Briefing & Strategic Memo Deliverable Synthesizer (inspired by Tencent WorkBuddy Goal-to-Document Workflows). Transforms raw multi-source enterprise findings into comprehensive, s

Enterprise Private Context & Role-Based Access Control (RBAC) Governance Sentinel (inspired by WeChat Work, Tencent Docs enterprise permissions). Inspects ingested context, classifies security clearan

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

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.

Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable info

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

Cryptographic Delegated Agentic Commerce Escrow & Settlement Ledger (inspired by Mastercard Agent Connect & Stripe Split-Settlements). Provides multi-party conditional escrow locking, autonomous proof

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

Long-Horizon Autonomous Task Checkpoint & Resumption Engine (inspired by Persistent Consumer & Enterprise Agents). Provides cryptographic event-sourcing state persistence, idempotency key deduplicatio

Model Context Protocol (MCP) JSON-RPC 2.0 proxy router with capability negotiation and dynamic tool dispatch

Open-source, LLM-agnostic capability runtime for AI agents — 97 skills as typed, permission-enforced MCP tools. Final certification: 23/23 gates PASS.

Universal Multi-Agent Mesh State Blackboard & Conflict Deconfliction Engine. Coordinates shared multi-agent state spaces, detects concurrent mutation race conditions, executes vector clock synchroniza

Autonomous Agentic Post-Purchase Tracking & Delivery Dispute Arbiter (inspired by Meta Muse, Shopify, Walmart, Instacart Post-Checkout Operations). Ingests carrier webhook events, tracks transit anoma

Autonomous Just-In-Time MCP Tool Synthesizer & Sandboxed Compiler (inspired by Manus Generalist Sandbox). Dynamically generates typed MCP tool schemas, validates Python execution AST trees against uns

Universal Multi-Agent Mesh State Blackboard & Conflict Deconfliction Engine. Coordinates shared multi-agent state spaces, detects concurrent mutation race conditions, executes vector clock synchroniza

Enterprise Executive Briefing & Strategic Memo Deliverable Synthesizer (inspired by Tencent WorkBuddy Goal-to-Document Workflows). Transforms raw multi-source enterprise findings into comprehensive, s

Autonomous Just-In-Time MCP Tool Synthesizer & Sandboxed Compiler (inspired by Manus Generalist Sandbox). Dynamically generates typed MCP tool schemas, validates Python execution AST trees against uns

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

Enterprise Knowledge Graph Provenance & Anti-Hallucination Tracer (inspired by Tencent Docs, Meeting & Enterprise Knowledge Bases). Provides cryptographic chunk hashing, reverse claim-to-source attrib

Enterprise Managed Agent Fleet Lifecycle Supervisor (inspired by Tencent WorkBuddy & Anthropic Managed Agents). Orchestrates worker agent registration, capability-based task dispatch, continuous heart

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

Sponsored Agent Intent Auction & Privacy-Preserving Ad Monetization Router (inspired by Sponsored Agents, Meta AI Ad Platform). Runs second-price Vickrey auctions matching consumer query intent with b

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

Autonomous Agentic Recurring Subscription Governance & Price Hike Autopilot (inspired by Stripe Billing, Mastercard Agent Connect recurring mandates, and SaaS spend optimizers). Detects recurring char

Real-time Multimodal Spatial Audio-Visual Grounding Engine (inspired by Meta Ray-Ban & Meta Muse). Fuses 2D/3D visual bounding boxes, user head-pose gaze vectors, and acoustic beamforming azimuth angl

Enterprise Presentation & Slide Deck Narrative Structure Compiler (inspired by Tencent WorkBuddy Goal-to-PPT Workflows). Transforms raw enterprise documents, meeting transcripts, and KPI metrics into

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

Enterprise Work Agent Goal-to-Artifact DAG Pipeline (inspired by WorkBuddy, Tencent Docs, WeChat Work Multi-Agent). Decomposes high-level business objectives into topological sub-tasks and directly sy

Long-Horizon Autonomous Task Checkpoint & Resumption Engine (inspired by Persistent Consumer & Enterprise Agents). Provides cryptographic event-sourcing state persistence, idempotency key deduplicatio

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.

RFC 6570 URI template parser and variable expansion engine for Model Context Protocol resources

RFC 6570 URI template parser and variable expansion engine for Model Context Protocol resources

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.

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

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

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

Manages MCP tool execution rate limits and compresses bloated tool response context payloads

Manages MCP tool execution rate limits and compresses bloated tool response context payloads

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.

🔍 Visualize any Claude Code agent harness — CLAUDE.md, subagents, skills, commands, hooks & MCP servers — as an interactive flow graph. Import from GitHub, ZIP, or local folder. 100% client-side.

Shared work-state for coding agents: claim work, leave handoffs, and generate review packets before PRs, over MCP.

Cẩm nang thực chiến Mastering Claude Code (tiếng Việt): 16 chương biên soạn từ tài liệu chính thức của Anthropic — CLI, workflows, MCP, subagents, skills, hooks, plugins, CI/CD & tối ưu context.

Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi

Exam-scored knowledge brains for AI agents: paste a docs URL, get a searchable brain over MCP with a measured score and known gaps. AGPL.

Secure execution for AI agents, on any machine. Connect any MCP client to the development environment on any machine you can run a command on (even your own laptop) - no open ports, no tunnels, and yo

Authoritative multi-agent software engineering coordinator with isolated Git worktrees, write scope locking, test verification, and serialized merge queue. (v0.1.0-beta).

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

Restyle your app without rebuilding it. Your built web app, 1:1, with its own knobs. MIT.

Evidence-first local MCP debugger for React, Vite, Next.js, Chromium, and Safari: reproduce, inspect, replay, and verify web bugs in one bounded workflow.

Local, capability-aware MCP server for authorized AI-assisted macOS and iOS debugging, Simulator/device workflows, Apple binary analysis, profiling, and reproducible evidence.

Open-source client for Novgraph, Novaya's proprietary hosted code knowledge graph. Gives coding agents recorded intent, related-code context, ranked change impact and architecture context over MCP or

Universal Context, Rules & Handoff Bridge for AI Coding Tools (Cursor, Copilot, Cline, Claude Code, Antigravity, MCP)

Djævin: calibrated local-first decision layer with a Devin ACP backend - no API key needed

Annotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server;

Smarter AI Development Workflows

Portal de arquitetura auto-hospedado + linguagem executável: catálogo verificado, landscape C4 com drill-in, governança (fitness functions e SLO por caminho crítico) e editor no browser. Binário Go ún

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.

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.

Universal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.

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

Find and fix what the MCP 2026-07-28 spec revision breaks in your server. 21 rules, 5 autofixers, and a readiness board.

A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client. Ghost the design first, light nodes up as they are built and verifie

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

A Visual Design that ships with your code. Agents and humans work together on the same canvas, where every change is a diffable JSX stored in a .uidx file inside your repo. Built on OpenPencil and Ski

An MCP server for discovering, ranking, and retrieving agent skills while minimizing context usage.

Sandboxed coding-agent workers for AI supervisors over MCP. Delegate tasks from Grok Bot or any MCP client to Kilo CLI or OpenCode running in per-task git worktrees inside bubblewrap, with any OpenAI-

Local gateway exposing OpenAI- and Anthropic-compatible endpoints backed by ChatGPT through an official MCP widget.

LayerMap MCP: a layered map of your codebase for coding agents: callers, callees and the impact of a change, for TypeScript, JavaScript, Go, Python and Java. MCP server, CLI, and plugins for Claude Co

Open-source control center for the OpenAI Secure MCP Tunnel: register local MCP servers (stdio/HTTP), run and supervise the official tunnel-client, and connect ChatGPT / Codex through a desktop app, l

Shared, persistent memory for your AI coding assistants (Claude Code, Copilot, Cursor, Gemini CLI, Codex…): a local MCP server and CLI that hand work over between tools automatically.

Git-native structural memory for AI coding agents. Index once — stays fresh on every pull, merge, and branch switch. MCP server for Claude Code, Cursor & any agent.

Convert AI coding sessions between Claude Code, Codex, OpenCode, Zed, Aider, Gemini CLI, Cursor, Cline & more — lossless, round-trip tested. MCP server + CLI.

One local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everyw

MCP server exposing the sources, public API and KDoc of Maven-published Kotlin/Java libraries

Live sidebar, ER diagrams, CLI, and MCP server for Django models. VS Code + PyPI + MCP Registry + Glama. Zero-dep parser, no DB required.

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

Give ChatGPT fast, safe, and auditable visibility into your VPS through MCP.

Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.

The agent-native Supabase killer: SQLite speed today, distributed cloud next, without the PostgreSQL tax.

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.

Public distribution surface for jarvis — local-first code intelligence MCP server (SCIP navigation + Zoekt search). Installer, Claude Code / Codex / Cursor plugins, and prebuilt binaries.

Shared long-term memory for AI coding agents — one local store for Claude Code, Codex CLI, opencode and anything that speaks MCP. SQLite + FTS5, no vector DB, $1-3/month.

MCP server for Plane: create, update, audit, and export work items from Codex and AI coding clients.

One window for every AI coding agent on your Mac. Sessions, skills, MCP servers, rules and dev processes across 219 agents — with real transcript conversion between them.

Coding agents are single-player: each session starts cold, in its own tool, blind to what the rest of the team already worked out. Motif makes your team's multiplayer — every Claude Code, Codex and Cu

Local-first MCP context engine for AI coding agents — cuts token cost ~90% via a per-project code graph + code folding. Works with Cursor, Claude Code, Codex & any MCP client. Web + ML/PyTorch codebas

One library of rules, skills, subagents and MCP servers for Claude Code, Codex, OpenCode, Gemini CLI and GitHub Copilot. Edit once, synced to every tool.

Find which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no AP

Multiplayer browser sessions for developers and AI coding agents

A map of all your repos for coding agents: one index, one card per repo, an MCP server. Works with Claude Code, Codex, Gemini CLI and Cursor.

Rust 插件中台：契约治理 · 注册发现 · 声明式编排 · 事件总线 · MCP 工具面 / Out-of-process plugin hub in Rust: contracts, discovery, DAG orchestration, event bus, MCP tool surface

Fast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).

Standalone Go runner and @9l/playwright SDK for bounded Playwright execution with validated receipts.

📱 Open-source multi-device responsive review and QA workspace for Chrome & Chromium browsers. Persistent previews, zero-reload geometry, and optional local MCP bridge.

SIMD-accelerated, single-pass codebase intelligence fabric for AI agents. Offload multi-keyword scans and AST context-pruning to native silicon.

Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI agents.

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

All-in-one MCP server. Agents get memory, tools, and coordination in one binary.

Convert AI coding CLI sessions between Codex, Claude Code, Pi, OpenCode, Devin, and Factory. SDK, CLI, MCP chat recall, and trace export for fine-tuning.

Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.

Free security & privacy scanner for AI-coded apps. 699 rules, 76 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for l

Native macOS SwiftUI dashboard for inspecting your ~/.claude config — skills, agents, settings, hooks, MCP servers, slash commands.

Self-hosted MCP server: your codebase as a knowledge graph, your secrets in an encrypted vault — both reachable by your AI assistant, and by nobody else.

Stop your AI agent from rebuilding what already exists. An opinionated MCP server that checks GitHub, npm and Python repos for maintained alternatives before you scaffold.

Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it

🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.

A token-frugal MCP server that gives coding agents structural understanding of a codebase: repo maps, symbol outlines, ranked search, import tracing, and parsed diagnostics — every result under a toke

YTAI: Python YouTube SDK, CLI, FastAPI API, and MCP server for search, metadata, transcripts, comments, and downloads without user-supplied API keys.

Repository-native Work, Docs, History and durable Memory for humans and AI agents — Markdown as the source of truth, with a local UI, CLI and MCP server

Skill + browser MCP for Claude Code and Codex: your app and browser reach domestic services over the real ISP while the agent stays on the VPN. Per-socket binding, per-host routing, no admin, nothing

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.

Local-first project state, task tracking, and context for coding agents.

Teach any coding agent the real s&box API: 17 source-verified reference files plus an 18-tool editor MCP toolset. Stops agents writing Unity code into Source 2 projects.

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

Deterministic AST Safety Guard, High-Throughput Compound Pipelines, Bidirectional Intent Synthesizer, Polyglot Graph & Zero-Dependency MCP Server in Pure Safe Rust.

Anti-hallucination guardrails for AI coding agents - hybrid Skill + MCP server (6 tools) that verifies code before it is marked done. Works with Claude Code, Cursor, VS Code, Copilot.

PL/SQL development for AI agents on Oracle Database - expert queries, impact analysis, and a snapshot-verified write path with honest rollback

Self-hosted, git-connected docs platform — push to deploy, docs.json + MDX, with a CLI and MCP server for AI-agent-native authoring.

Delegate Grok Bot coding work to your own local Claude Code / Codex CLIs via a custom MCP connector

IEEE Computer Society Universal Developer Operations, Diagnostics & AlgoJudge Competitive Execution MCP Server

A local-first coordination hall for long-running AI collaboration.

Official GoAnyAPI MCP server — connect AI agents to web data, Google Search, SEO, backlinks, Google Ads Transparency, traffic, domain intelligence, and more APIs.

Switch between multiple Claude Code accounts with one command — MCP servers, plugins, skills and session history stay shared.

Local-first Build Truth & verification layer for AI coding agents. Stops hallucinations, cuts token costs by 90%, and fixes monorepo test failures for Claude, Cursor, Aider, & Copilot.

The task tracker your AI agents keep for each other: every task carries a case file, so the next agent picks up where the last one stopped. MCP server + live board. Self-hosted, one-line install.

Turn OpenAPI specs, GraphQL schemas, and existing MCP servers into typed tools for AI agents. An API-to-MCP platform with a dashboard, CLI, and TypeScript/Python clients: deterministic endpoint mappin

Secure Model Context Protocol (MCP) server & gateway for Claude, Cursor, and ChatGPT. Unlimited local file editing, testing, and dev tools without cloud limits.

Run Claude Code, Codex, Grok & Pi on machines far from you — native TUI over plain SSH. Nothing installed on the server, API keys stay remote, sessions survive the laptop closing.

The content layer for your website. Open-source SDK, MCP server, CLI, and framework integrations.

Model your API as a graph once. Long-chain integration tests, layer × environment matrices, CI-ready runs, and an MCP server — all from the same YAML.

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default,

Self-hosted MCP bridge for local files, search, editing, shell sessions, Git, and SSH.

AI usage and cost in your macOS menu bar: live rate limits for Claude, OpenAI and Gemini, ccusage-style costs from local logs, MCP server for model routing

Free, source-available desktop GraphQL client and IDE for macOS, Linux and Windows: tabs that survive crashes, collections in git-friendly files, environments that refresh tokens, flows as smoke tests

Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.

Evidence-first code intelligence for AI coding agents: verified claims with evidence, honest unknowns, a name check for Python and Java (invented APIs, Mixin targets), PDF/Office documents and screens

High-performance Model Context Protocol (MCP) server & CLI for C and C++: offline cppreference, semantic code analysis (clangd + xmake/CMake), Core Guidelines, SEI CERT, and compiler matrix.

🖱️ Let Factory Droid control your Mac with the Codex app's Computer Use tool. One-command install, no approval forms, works with any Codex install path.

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

Command line for mcp.tc, the MCP server directory: search servers, add them to Claude Code, Cursor, VS Code and other clients with each vendor's own URL, and build and check your own.

Codex MCP server: run parallel Codex CLI workers in isolated git worktrees, state on disk, web dashboard, auto-update.

See the tokens Claude Code and Codex load before you type: MCP tool lists, skills, hooks, CLAUDE.md and AGENTS.md per session. Find what you never use and archive it, with undo. Open source, runs offl

Audit and revoke everything Claude Code has been given on Linux: trusted folders, "always allow" rules, saved transcripts, hooks, MCP servers. Quarantine instead of delete, one command to undo. Single

Plan, apply, and revert one agent development environment (MCP servers, skills, instructions, settings, plugins, and config files) across 10 coding agents. CLI and TypeScript SDK.

A task manager your AI agents keep themselves. Claude Code, Codex and Gemini CLI create, start and close their own tasks over MCP; hooks keep the board honest. Self-hosted, English and Russian.

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