Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

DevDocs MCP Server

Self-hosted documentation crawler and Markdown MCP server that lets Claude query crawled technical documentation, list files, read sections, search content, inspect metadata, and keep generated Markdown in sync.

by CyberAGI·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • DevDocs runs a multi-container Docker stack with frontend, backend, MCP, and Crawl4AI services.
  • The crawler can fetch and process external websites, so review crawl targets, rate limits, robots rules, and site terms before crawling.
  • The backend and crawler use a Crawl4AI API token; replace the demo token before shared or production use.
  • The MCP container mounts generated Markdown and logs, and its tools can read, search, sync, and expose that content to the MCP client.
  • Local services are exposed on development ports by the Docker stack; do not expose them on untrusted networks without authentication and network controls.

Privacy notes

  • Crawled pages, generated Markdown, JSON metadata, source URLs, tags, search queries, local logs, and MCP tool outputs may contain proprietary documentation, customer data, internal architecture, or third-party website content.
  • The Markdown MCP server can reveal full document text, section contents, table of contents, metadata, and search snippets to the connected model provider.
  • Logs, crawl results, mounted volumes, and container transcripts can retain documentation-derived content after an MCP session ends.
  • Optional LLM-related Crawl4AI environment variables can route documentation-derived content to external model providers if configured.
  • Keep storage directories, crawl outputs, API tokens, and generated documentation artifacts out of public repositories unless publication is explicitly approved.

Prerequisites

  • Docker and Docker Compose available on the host that will run DevDocs.
  • Git access to clone the DevDocs repository and run the Docker startup script.
  • MCP client support for launching stdio servers through `docker exec -i`.
  • Documentation URLs reviewed for crawling permissions, robots rules, and terms of service.
  • Storage, logs, crawl results, and Markdown output directories scoped to documentation you are authorized to crawl and query.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Apache-2.0-licensed open-source project. The entry focuses on the repository's Docker-backed Fast Markdown MCP server and documentation-crawling workflow.
Full copyable content
{
  "mcpServers": {
    "fast-markdown": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "devdocs-mcp",
        "python",
        "-m",
        "fast_markdown_mcp.server",
        "/app/storage/markdown"
      ]
    }
  }
}

About this resource

Content

DevDocs combines a documentation crawler, a local web UI, and a Docker-backed Fast Markdown MCP server. The crawler writes documentation into local Markdown and metadata files, while the MCP server exposes those files to Claude through tools for listing files, reading Markdown, searching content, finding tagged documents, inspecting sections, and getting document statistics.

Use it when you want Claude to work from a private or self-hosted copy of technical documentation instead of repeatedly searching the live web. The upstream Docker setup runs the MCP process over stdin/stdout through docker exec -i, so the client communicates with the devdocs-mcp container rather than a public network endpoint.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, MCP Docker setup guide, Claude MCP settings, Dockerfiles, Compose file, Python package metadata, MCP server implementation, and document-structure parser for current behavior.

Features

  • Crawl and store technical documentation as Markdown and JSON metadata.
  • Run a local Fast Markdown MCP server inside the DevDocs Docker stack.
  • List available Markdown files.
  • Read full Markdown files with basic metadata.
  • Search across generated Markdown content.
  • Search metadata tags.
  • Return document statistics.
  • Retrieve a specific section by generated section ID.
  • Generate a table of contents from Markdown headings.
  • Run advanced section search with ranking and confidence scores.
  • Watch Markdown and metadata files so changes can be synchronized.

Installation

Clone the repository and start the Docker stack using the upstream scripts:

git clone https://github.com/cyberagiinc/DevDocs.git
cd DevDocs
./docker-start.sh

Connect Claude or another MCP client to the containerized MCP process:

{
  "mcpServers": {
    "fast-markdown": {
      "command": "docker",
      "args": [
        "exec",
        "-i",
        "devdocs-mcp",
        "python",
        "-m",
        "fast_markdown_mcp.server",
        "/app/storage/markdown"
      ]
    }
  }
}

Restart the MCP client after changing its server configuration. Keep the generated Markdown storage mounted only where DevDocs and the approved MCP client need access.

Use Cases

  • Give Claude a searchable local copy of framework or library docs.
  • Crawl internal engineering documentation for private agent workflows.
  • Ask Claude to find relevant sections across generated Markdown docs.
  • Query a table of contents before reading a large document.
  • Keep documentation snapshots available when live pages change.
  • Build a local research workflow around Crawl4AI output and Markdown MCP search.

Safety and Privacy

DevDocs can crawl websites and convert them into model-visible local Markdown. Before crawling, confirm that the target permits automated access and that the depth, concurrency, and selected URLs are appropriate. Avoid crawling customer portals, authenticated pages, or internal knowledge bases unless you have explicit approval and a retention plan.

The MCP server exposes generated Markdown files, metadata, sections, tags, search snippets, and document statistics to the connected model provider. Treat the storage, logs, and crawl_results directories as sensitive. Replace the default Crawl4AI demo token before shared use, avoid exposing local service ports on untrusted networks, and keep optional LLM provider API keys out of logs, shell history, screenshots, and repository files.

Duplicate Check

No cyberagiinc/DevDocs, DevDocs MCP Server, Fast Markdown MCP from DevDocs, or matching source URL entry was found in content/mcp or README.md.

#documentation#crawler#markdown#docker#developer-tools

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.