myst-mcp
Enables searching any MyST Markdown or Jupyter Book documentation site that publishes a search index, without crawling or embeddings.
README
myst-mcp
myst-mcp is an MCP server for searching any MyST Markdown or Jupyter Book documentation site that publishes myst.search.json. It consumes the static search index that MyST already builds, so it does not crawl pages, host a backend, or require embeddings.
MyST is the document engine and Jupyter Book is a distribution of it. The myst.search.json index is produced at the MyST engine layer, which means this package works across book-theme, article-theme, custom themes, Jupyter Book, and plain mystmd sites.
Usage
npx -y myst-mcp <site-url-or-local-path> ["Human description of these docs"]
Examples:
npx -y myst-mcp https://your-myst-site.example "Example MyST docs"
{
"mcpServers": {
"my-docs": {
"command": "npx",
"args": ["-y", "myst-mcp", "https://your-myst-site.example", "Example MyST docs"]
}
}
}
Claude Code:
claude mcp add my-docs -- npx -y myst-mcp https://your-myst-site.example "Example MyST docs"
Tools
search_docs
Input:
{ "query": "installation", "limit": 10 }
Returns search hits with title, section, breadcrumb, absolute URL, snippet, type, and score.
fetch_page
Input:
{ "url": "/getting-started/" }
Returns the page title and LLM-friendly Markdown reconstructed from all matching search index records in document order. Full URLs and anchor URLs are accepted.
Supported sources
- Remote MyST sites, loaded from
<base>/myst.search.json - Local MyST site build directories containing
myst.search.json - A direct local path to
myst.search.json
The server requires MystSearchIndex version "1" and fails clearly if the file is missing, invalid, or from an unsupported future version.
Development
pnpm install
pnpm build
pnpm test
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.