Deepwiki MCP Server
by regenrek
An unofficial Deepwiki MCP Server that crawls Deepwiki URLs, converts them to Markdown, and returns either a single document or a list of pages. It's designed to be used with MCP-compatible clients like Cursor AI.
Last updated: N/A
What is Deepwiki MCP Server?
The Deepwiki MCP Server is a tool that fetches content from Deepwiki URLs, sanitizes the HTML, rewrites links, and converts the content into Markdown format. It can return the entire content as a single document or as a structured list of pages.
How to use Deepwiki MCP Server?
To use the server, configure your MCP client (like Cursor AI) to use the deepwiki_fetch tool. Provide the Deepwiki URL, choose the output mode (aggregate or pages), and optionally set the maximum crawling depth. Example configurations are provided in the README for both local development and direct API calls.
Key features of Deepwiki MCP Server
Domain Safety: Only processes URLs from deepwiki.com
HTML Sanitization: Strips headers, footers, navigation, scripts, and ads
Link Rewriting: Adjusts links to work in Markdown
Multiple Output Formats: Get one document or structured pages
Performance: Fast crawling with adjustable concurrency and depth
NLP: It's to search just for the library name
Use cases of Deepwiki MCP Server
Fetching documentation from Deepwiki and converting it to Markdown for use in other applications.
Integrating Deepwiki content into MCP-compatible clients like Cursor AI.
Creating a local copy of a Deepwiki repository in Markdown format.
Searching for specific information within a Deepwiki repository using command line prompts.
FAQ from Deepwiki MCP Server
What domains are allowed?
What domains are allowed?
Only deepwiki.com domains are allowed for security reasons.
How can I configure the server?
How can I configure the server?
You can configure the server using environment variables such as DEEPWIKI_MAX_CONCURRENCY, DEEPWIKI_REQUEST_TIMEOUT, DEEPWIKI_MAX_RETRIES, and DEEPWIKI_RETRY_DELAY.
What output formats are supported?
What output formats are supported?
The server supports two output formats: 'aggregate' for a single Markdown document and 'pages' for structured page data.
How do I handle timeout errors?
How do I handle timeout errors?
For large repositories, consider increasing the timeout and concurrency using the DEEPWIKI_REQUEST_TIMEOUT and DEEPWIKI_MAX_CONCURRENCY environment variables.
How do I contribute to the project?
How do I contribute to the project?
Please see the CONTRIBUTING.md file for details on how to contribute.