Server facts
Deepwiki MCP Server
Project
- Author
- regenrek
- Repository
- github.com/regenrek/deepwiki-mcp
- License
- MIT
- Category
- Files & Documents
Tech
- Runtime / language
- node
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 1,385
- Last commit
- Data as of
Tags
- Deepwiki
- Documentation
- Markdown
- Unofficial
- Web Crawling
Overview
Deepwiki MCP Server is an unofficial documentation crawler built around DeepWiki pages. Its documented workflow accepts a starting repository URL, visits relevant pages, removes surrounding website clutter, and converts the result to Markdown. Assistants can request either one combined document or separate page records. This design targets developers who want repository documentation in a format suitable for further reading and analysis inside an MCP conversation.
The most important qualification appears at the top of the README: the server is currently not functioning because DeepWiki has blocked scraping. The project recommends the official DeepWiki MCP service instead. The remaining documentation explains the intended behavior, not a guarantee of current access. That distinction applies to examples for complete documentation retrieval, individual pages, repository shorthand, and library-name prompts. Changing client configuration alone is not presented as a fix for the upstream restriction.
The described tool supports aggregate and page-based output with a crawl-depth limit. Domain checks restrict requests to deepwiki.com, while sanitization removes navigation and scripts and link rewriting prepares the output for Markdown. Response examples include page counts, byte totals, elapsed time, and partial failures. Local installation uses npx or a source build, with configurable concurrency, timeouts, and retries. HTTP examples are included, but Docker deployment is explicitly labeled untested. These details may help evaluate the implementation, while the outage notice should guide present-day adoption.
Install & configure
Requirements
- Node.js and npx
- An MCP-compatible client
npx -y mcp-deepwiki@latestThis is the README's Cursor launch configuration, not a remedy for blocked scraping. The README recommends the official DeepWiki MCP service because this implementation is currently nonfunctional.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"deepwiki-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-deepwiki@latest"
],
"env": {
"DEEPWIKI_MAX_CONCURRENCY": "<optional simultaneous request limit>",
"DEEPWIKI_REQUEST_TIMEOUT": "<optional request timeout in milliseconds>",
"DEEPWIKI_MAX_RETRIES": "<optional retry count>",
"DEEPWIKI_RETRY_DELAY": "<optional retry-backoff base in milliseconds>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"deepwiki-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-deepwiki@latest"
],
"env": {
"DEEPWIKI_MAX_CONCURRENCY": "<optional simultaneous request limit>",
"DEEPWIKI_REQUEST_TIMEOUT": "<optional request timeout in milliseconds>",
"DEEPWIKI_MAX_RETRIES": "<optional retry count>",
"DEEPWIKI_RETRY_DELAY": "<optional retry-backoff base in milliseconds>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"deepwiki-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-deepwiki@latest"
],
"env": {
"DEEPWIKI_MAX_CONCURRENCY": "<optional simultaneous request limit>",
"DEEPWIKI_REQUEST_TIMEOUT": "<optional request timeout in milliseconds>",
"DEEPWIKI_MAX_RETRIES": "<optional retry count>",
"DEEPWIKI_RETRY_DELAY": "<optional retry-backoff base in milliseconds>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"deepwiki-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-deepwiki@latest"
],
"env": {
"DEEPWIKI_MAX_CONCURRENCY": "<optional simultaneous request limit>",
"DEEPWIKI_REQUEST_TIMEOUT": "<optional request timeout in milliseconds>",
"DEEPWIKI_MAX_RETRIES": "<optional retry count>",
"DEEPWIKI_RETRY_DELAY": "<optional retry-backoff base in milliseconds>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"deepwiki-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-deepwiki@latest"
],
"env": {
"DEEPWIKI_MAX_CONCURRENCY": "<optional simultaneous request limit>",
"DEEPWIKI_REQUEST_TIMEOUT": "<optional request timeout in milliseconds>",
"DEEPWIKI_MAX_RETRIES": "<optional retry count>",
"DEEPWIKI_RETRY_DELAY": "<optional retry-backoff base in milliseconds>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| deepwiki_fetch | Designed to crawl DeepWiki documentation and return combined Markdown or per-page records. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Evaluate the documented design for turning repository documentation into Markdown.
- Inspect the intended aggregate versus per-page documentation outputs.
- Assess an existing installation before migrating to the official DeepWiki service.
Strengths
- Documents combined and per-page Markdown outputs.
- Restricts crawling to the DeepWiki domain.
- Includes configurable crawl depth, concurrency, and retries.
Limitations
- The README reports the server currently does not work because scraping is blocked.
- It is an unofficial integration.
- Docker deployment is documented as untested.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
