AI Documentation & Guru Knowledge MCP Server
@LaserFocused-ee
About AI Documentation & Guru Knowledge MCP Server
MCP server for providing documentation to Claude
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ai-docs-mcp": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"--cli",
"node",
"dist/index.js",
"\\"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is AI Documentation & Guru Knowledge MCP Server?
This MCP server provides AI assistants like Claude with structured access to local development documentation and Guru knowledge base content. It serves as a bridge between AI tools and your organization's knowledge repositories, enabling intelligent retrieval of coding guidelines, architecture patterns, troubleshooting guides, and institutional knowledge.
How to use AI Documentation & Guru Knowledge MCP Server?
Install Node.js >=20, clone the repository, run npm install and npm run build, then set the GURU_TOKEN environment variable (format: username:token). Integrate with Claude Desktop by adding the server to your MCP configuration file (mcp-config.json). The server offers five tools: legacy-list-docs, legacy-read-doc, guru-list-cards, guru-read-card, and guru-get-card-attachments.
Key features of AI Documentation & Guru Knowledge MCP Server
- Tool-first architecture for well-defined access
- Dual knowledge sources: local docs and Guru
- Powerful search across both documentation and cards
- Rich metadata for documents and knowledge cards
- Modular design with clean separation of concerns
- Secure credential handling via environment variables
Use cases of AI Documentation & Guru Knowledge MCP Server
- Access coding guidelines and architecture patterns for multiple tech stacks (Flutter, React, NestJS, Git)
- Search and read Guru knowledge base cards for procedures, troubleshooting, and runbooks
- Discover available documentation before reading specific files
- Retrieve attachments (screenshots, diagrams) from Guru cards
- Provide context-aware development guidance to AI assistants like Claude
FAQ from AI Documentation & Guru Knowledge MCP Server
How do I obtain and configure Guru API credentials?
Go to your Guru account Settings → API Access, generate a token, and format it as your_email:your_api_token. Set this value in the GURU_TOKEN environment variable when configuring the MCP server.
What are the system requirements?
Node.js version 20.0.0 or higher is required. The server runs cross-platform on macOS, Linux, and Windows.
How is documentation structured locally?
Local docs are organized under the docs/ directory with categories like code_guidelines/flutter, code_guidelines/react, code_guidelines/nestjs, code_guidelines/git, and service-docs.
What tools are available and what do they do?
Five tools: legacy-list-docs (list docs by category), legacy-read-doc (read a specific doc), guru-list-cards (search Guru cards with filters), guru-read-card (full card content), and guru-get-card-attachments (list/download card attachments).
Are there any known limits or rate limits?
Guru API calls are subject to rate limiting. The guru-list-cards tool enforces a maximum of 50 results per request.
More Memory & Knowledge MCP servers
mcp-local-rag
nkapila6"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
JupyterMCP - Jupyter Notebook Model Context Protocol Integration
jjsantos01A Model Context Protocol (MCP) for Jupyter Notebook
Anytype MCP Server
anyprotoAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
Semantic Scholar MCP Server
YUZongminA FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
Obsidian MCP Server
cyanheadsRead, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
Comments