📡 MCP Radar

RitualDev-Lab/SkillPrism

Progressive Skill Disclosure & Context Compaction Engine for Autonomous AI Coding Agents. Reduces prompt token bloat by 96.7% using JIT discovery, ephemeral schema injection, and semantic receipts.

⭐ 3 stars
⑂ 3 forks
TypeScript
momentum ▲ 36.0
created 2026-10-14
on radar since 2026-10-15
ai-agentsai-agents-and-toolsai-agents-cliai-agents-mcpmcpmcp-clientmcp-servermcp-serversmcp-tools
View on GitHub ↗Homepage ↗

About SkillPrism

Progressive Skill Disclosure & Context Compaction Engine for Autonomous AI Coding Agents Preloading hundreds of enterprise tool schemas dilutes model attention and inflates token costs. SkillPrism indexes skills out-of-context and injects only what the model needs, right when it needs it.

⚡ The Problem: Context Bloat & Attention Dilution

When autonomous coding agents (Claude Code, Cursor, Windsurf, Antigravity) connect to enterprise MCP servers or large API catalogs: ~24,500 Tokens Wasted: Full JSON schemas for hundreds of endpoints are dumped into the system prompt on turn 1. Model Hallucinations: When models face 100+ tools, tool selection accuracy drops dramatically ("Lost in the Middle"). Token Cost Explosion: Every reasoning turn repeatedly transmits schemas the agent never touches.

💡 The Solution: SkillPrism Progressive JIT Disclosure

SkillPrism moves the entire tool catalog outside the LLM context: 1. Zero-State (~199 tokens): The agent prompt starts with only two meta-tools: searchskills and loadskill. 2. Sub-Millisecond BM25 Hybrid Search (

🚀 Founder & Lead 🔑 Direct Access Admin

🎨 Core Maintainer & Product 🔑 Direct Access Admin

⚙️ Core Maintainer & Infra 🔑 Direct Access Admin

Huge thanks to all our open-source Contributors! We warmly welcome issues, feedback, and pull requests.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/RitualDev-Lab--SkillPrism.html)

Related MCP servers

codeztech-atique/500-AI-Agents-Projects

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

⭐ 3Python
mkpoli/gmail-mcp

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

⭐ 5TypeScript
priyansh-narang2308/TheBlacklisted-NitroStack

Protocol-0 is an MCP (Model Context Protocol) server that gives AI assistants, Claude, Cursor, ChatGPT, NitroChat, or any MCP-compatible client, real authority to act as your Site Reliability Engineer

⭐ 4TypeScript
FrancisTCE/gresui-web

simple postgres ui + mcp service layer. NPM: https://www.npmjs.com/package/gresui-web

⭐ 3TypeScript
felipedamacenoteodoro/mcp-google-flow

MCP server for controlling Google Flow (Veo, Nano Banana) with AI agents from your own browser.

⭐ 3TypeScript
RitualDev-Lab/AgentShield

Enterprise-Grade Zero-Leak Secret Defense & Sandbox for Autonomous AI Coding Agents (Claude Code, Cursor, Windsurf, Codex, Antigravity)

⭐ 3TypeScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.