ref-tools-mcp
Helps AI coding agents efficiently access public or private library documentation, reducing context window waste.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 1.1k
- Source
- mcp-github
- Repository
- github.com/ref-tools/ref-tools-mcp
Overview
Ref MCP is a ModelContextProtocol server that provides API, service, and library documentation access for AI coding tools or agents. It maintains agent access to documentation in a fast and token-efficient manner. Designed to match model search patterns while minimizing context usage to prevent context degradation. Supports filtering search results and extracting relevant sections from pages, improving efficiency and lowering costs.
Capabilities
- ▪Efficient technical documentation search
- ▪Extract content from URLs and convert to Markdown
- ▪Track search history to minimize context usage
- ▪Filter duplicate search results
- ▪Extract most relevant parts of documentation
Use cases
Setup
Recommended to use HTTP server: \
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
Related skills
pstack-claude
Provides rigorous workflows for multiple agents, supporting Claude Code, Codex, and more.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.