"MDN Web Docs" matching MCP servers:

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

A self-hosted MCP server that crawls, indexes, and searches documentation from any website locally, including private sites requiring authentication. It provides hybrid search capabilities and local embedding generation to maintain privacy while keeping AI assistant knowledge up to date.

MCP server for searching web documentation via sitemap.xml, enabling semantic search across multiple documentation sites using Ollama embeddings.

Enables semantic search over Databricks docs, API reference, Terraform provider docs, and knowledge base via tools like search_databricks_docs and research.

Enables adding a cite-or-refuse answer box to your docs from your agent.

A fast, dependency-light MCP server that converts web pages into clean Markdown, structured metadata, and classified links for language models.

Enables agents to perform full-text search and read Hermes Agent documentation offline from a local cache, without scraping the site.

Index docs websites and local folders, then let Claude, Cursor, or any MCP client answer from the current docs, with a link to every section it used.

An MCP server that runs Apify scraping actors with quality-gated validation, scoring, and retries, returning embedding-ready chunks for AI agents.

Enables semantic search over ByJG's documentation, letting LLMs answer questions about ByJG libraries and cite the pages where answers were found.

MCP server for the StitchAPI docs: search_docs (hybrid BM25+vector) + get_doc. Local/offline npm package (@stitchapi/docs-mcp, docs bundled, no per-query network) and a hosted Streamable-HTTP server (stitchapi.dev/api/mcp).

Provides semantic search over AWS Cloudscape Design System documentation using natural language queries, enabling AI assistants to efficiently find and retrieve component documentation with token-efficient responses.

Enables MCP-capable agents to query a LightRAG knowledge graph for grounded answers with source files, ingest documents into the index, and retrieve indexing statistics.

MCP server providing a searchable knowledge base for the AT Protocol ecosystem, including protocol docs, lexicons, Bluesky API docs, and cookbook examples.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Lets AI agents search and read a folder of Markdown documentation at query time, exposing heading-level search, whole-page or section retrieval, and page listing as tools and resources over stdio or Streamable HTTP. Can run as a CLI, a hosted endpoint, or a library inside an existing Node or Next.js site.

Enables local, offline BM25 search and retrieval of NeoForge documentation through MCP tools, including section/doc access, API symbol lookup, page listing, and cross-version comparison.

Enables AI agents to fetch any web page and receive clean, token-efficient Markdown, escalating only as needed from direct HTTP with browser TLS fingerprints to headless-browser rendering and residential proxies when a site blocks access. Supports question-focused passage retrieval with BM25 ranking, pagination, caching, JS rendering control, and safe-by-default restrictions on local and private-network URLs.

An enterprise-grade Model Context Protocol server for high-performance web analysis that discovers subpages, provides AI-based page summaries, and extracts structured content for RAG using FastMCP and FastAPI.

A focused MCP server that provides a single web_search tool for web searches, integrating Tavily and Brave with automatic fallback and key rotation.