PluginBench
MCP Server
Active
MIT

ai.smithery/docfork-mcp MCP Server

ai.smithery/docfork-mcp

Up-to-date library documentation for AI coding agents — now shut down (offline since June 14, 2026).

What is the ai.smithery/docfork-mcp MCP server?

Docfork MCP is a Model Context Protocol server that provides AI coding agents (Cursor, Claude Code, Windsurf, etc.) with up-to-date documentation and code examples for 9000+ libraries. It exposes search_docs and fetch_doc tools so agents can look up current API signatures instead of relying on stale training data. Note: as of June 14, 2026, Docfork has shut down and the MCP server, CLI, and hosted endpoints are offline.

Docfork MCP served ranked, up-to-date documentation directly into AI coding agents like Cursor, Claude Code, and Windsurf, aiming to prevent hallucinated or outdated API usage. It offered a search_docs tool for ranked documentation sections and a fetch_doc tool for full rendered markdown from a documentation URL, along with a companion "dgrep" CLI for terminal-based searches. It also supported indexing custom public or private GitHub repositories as searchable libraries for internal APIs, SDKs, and runbooks. As of June 14, 2026, the service has shut down and all endpoints, API keys, and the CLI no longer function.

How to install ai.smithery/docfork-mcp

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • Authorization
    required
    secret

    Bearer token for Smithery authentication

Cursor
~/.cursor/mcp.json
{
  "mcpServers": {
    "docfork-mcp": {
      "url": "https://server.smithery.ai/@docfork/mcp/mcp"
    }
  }
}
Windsurf
~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "docfork-mcp": {
      "serverUrl": "https://server.smithery.ai/@docfork/mcp/mcp"
    }
  }
}
VS Code
.vscode/mcp.json
{
  "servers": {
    "docfork-mcp": {
      "type": "http",
      "url": "https://server.smithery.ai/@docfork/mcp/mcp"
    }
  }
}
Claude Desktop
Claude Desktop connects to remote servers via the mcp-remote bridge.
{
  "mcpServers": {
    "docfork-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://server.smithery.ai/@docfork/mcp/mcp"
      ]
    }
  }
}
Claude Code
claude mcp add --transport http docfork-mcp https://server.smithery.ai/@docfork/mcp/mcp

Tools & capabilities

Tools this server exposes to the agent.

  • search_docsReturns ranked documentation sections with titles, URLs, and relevance scores for a given library and query.
  • fetch_docReturns full rendered markdown content from a specific documentation URL.

Use cases

  • Look up current, non-hallucinated API signatures and usage examples while coding in Cursor, Claude Code, or Windsurf
  • Search terminal-side for documentation snippets via the dgrep CLI (e.g., dgrep search)
  • Index a private or public GitHub repo as a custom library so internal APIs, SDKs, or runbooks are searchable by agents
  • Scope documentation search to a project's declared dependencies via dgrep init reading package.json
  • Share versioned library sets (Cabinets) and API keys across a team for consistent documentation lookups

ai.smithery/docfork-mcp MCP server FAQ

Is Docfork MCP still available?

No. Docfork shut down as of June 14, 2026. The MCP server, CLI, and all hosted endpoints are offline, API keys no longer work, and 'npx dgrep setup' will fail.

What did Docfork MCP do?

It served up-to-date documentation and code examples for 9000+ libraries directly to AI coding agents via two tools: search_docs (ranked doc sections) and fetch_doc (full markdown content).

Was Docfork free to use?

It offered a free tier of 1,000 requests per month per organization, with paid plans for teams needing higher usage and shared API keys/Cabinets.

How was Docfork installed in Cursor or Claude Code?

Via 'npx dgrep setup' for automatic configuration, or manually by adding an MCP server entry pointing to https://mcp.docfork.com/mcp (or the /oauth variant) in the client's mcp.json config, optionally with a DOCFORK_API_KEY header.

Did Docfork require authentication?

No API key was needed for initial sign-in via the setup flow; teams could optionally use a DOCFORK_API_KEY header or OAuth for authenticated remote HTTP connections.

How was Docfork different from Context7?

Docfork scoped searches to a project's declared dependencies via dgrep init, cached resolved package identifiers to avoid repeated resolution, and used hybrid semantic + BM25 search with AST-aware chunking.

README (reference)

Source of truth, from the repository.

<p align="center"> <a href="https://docfork.com"> <picture> <source srcset="logo_light.png" media="(prefers-color-scheme: dark)"> <source srcset="logo_dark.png" media="(prefers-color-scheme: light)"> <img src="logo_dark.png" alt="Docfork" height="40" /> </picture> </a> </p>

[!CAUTION] Docfork has shut down as of June 14, 2026. The MCP server, CLI, and all hosted endpoints are offline and will not return. API keys no longer work, and npx dgrep setup will fail. Thank you to everyone who used the service.

<p align="center">Up-to-date docs for AI coding agents.</p>

AI agents hallucinate APIs, bloat context with stale docs, and write code against outdated signatures. Docfork serves up-to-date documentation directly in Cursor, Claude Code, and Windsurf.

Without Docfork

  app.use('/api/*', jwt({ secret: ... }))
-                       ^^^ removed in Hono v4

With Docfork

  app.use('/api/*', bearerAuth({ verifyToken: ... }))
+                       ^^^ current API, Hono v4.2

Get Started

npx dgrep setup

Installs the Docfork MCP server in your IDE. Detects your installed agents and writes the config file; sign in to Docfork on first use, no API key needed. Target one with --agent claude-code (also: cursor, codex, opencode, vscode, windsurf, amp, factory, zed).

Your agent now has two tools:

ToolReturns
search_docsRanked documentation sections with titles, URLs, and relevance scores.
fetch_docFull rendered markdown content from a documentation URL.

No prompt suffix needed:

Set up server-side rendering with Next.js App Router.

Or search from the terminal:

dgrep search "middleware redirect based on authentication" -l vercel/next.js
dgrep search "server actions with forms" -l vercel/next.js

Quickstart → · dgrep docs → · CLI reference →

Your own docs

Index any public or private GitHub repository as a custom library. Your internal APIs, SDKs, and runbooks become searchable by your agents — same pipeline as public libraries. GitHub integration setup →

Teams

Free: 1,000 requests/month per organization. For team rollout, commit the MCP config to your repo:

// .cursor/mcp.json (committed to git, picked up by every engineer)
{
  "mcpServers": {
    "docfork": {
      "url": "https://mcp.docfork.com/mcp",
      "headers": {
        "DOCFORK_API_KEY": "YOUR_TEAM_API_KEY"
      }
    }
  }
}

Share API keys and Cabinets across your organization. Docfork doesn't store your code or prompts. Security → · Pricing →

MCP Setup

[!TIP] Run npx dgrep setup to install automatically (use --agent claude-code to target one). Manual config below for other clients.

Cursor<a href="https://cursor.com/en/install-mcp?name=docfork&config=eyJ1cmwiOiJodHRwczovL21jcC5kb2Nmb3JrLmNvbS9tY3AifQ%3D%3D"><img src="https://cursor.com/deeplink/mcp-install-dark.svg" height="20" alt="Add to Cursor"/></a>

{
  "mcpServers": {
    "docfork": {
      "url": "https://mcp.docfork.com/mcp",
      "headers": {
        "DOCFORK_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Claude Code

claude mcp add --transport http docfork https://mcp.docfork.com/mcp/oauth

OpenCode

{
  "mcp": {
    "docfork": {
      "type": "remote",
      "url": "https://mcp.docfork.com/mcp",
      "headers": { "DOCFORK_API_KEY": "YOUR_API_KEY" },
      "enabled": true,
    },
  },
}

Don't see your client? Setup guides for all 29 supported clients →

OAuth Authentication

Docfork supports MCP OAuth specs. Change your endpoint to use OAuth:

- "url": "https://mcp.docfork.com/mcp"
+ "url": "https://mcp.docfork.com/mcp/oauth"

Note: OAuth is for remote HTTP connections only. View full OAuth guide →

Agent Rule

Add a rule so your agent calls Docfork MCP automatically. Full rule and IDE-specific setup →

[!NOTE] Add Rule to Cursor (One-Click)

Claude Code — add to your CLAUDE.md:

## Docfork policy

Use Docfork MCP `search_docs` and `fetch_doc` tools for library/API docs, setup, and configuration questions.

- Start `library` with a short name or keyword (e.g., `nextjs`, `zod`). Use the `owner/repo` from the result URL for follow-up calls, never guess it upfront.
- After finding a relevant result, call `fetch_doc` to get the full content. Search results are summaries only.
- Prefer Docfork results over training data when they conflict.
<details> <summary>Full rule (all clients)</summary>
When writing or debugging code that involves third-party libraries, frameworks, or APIs, use Docfork MCP `search_docs` and `fetch_doc` tools rather than relying on training data.

**Two defaults to follow every time:**

- Start `library` with a short name or keyword (e.g., `nextjs`, `zod`). Use the `owner/repo` from the result URL for follow-up calls, never guess it upfront.
- After finding a relevant result, call `fetch_doc` to get the full content. Search results are summaries only.

Skip Docfork when:

- Language built-ins, general algorithms, syntax stable across versions
- Code or docs the user has already provided in context

When uncertain, default to using Docfork.
</details>

FAQ

How is Docfork different from Context7? Both provide MCP servers and CLIs for searching library documentation. Here are the key differences:

  • Stack scoping. dgrep init reads your package.json and scopes all searches to your declared dependencies. Cabinets let you version-pin those libraries across a team.
  • Resolve once, search many. dgrep init resolves package names to canonical identifiers once and caches the mapping in .dgrep/config.json. No per-query resolution step.
  • Hybrid search. Semantic search and BM25 run in parallel, fused via Reciprocal Rank Fusion. AST-aware chunking preserves function boundaries.

Does Docfork store my code or prompts? Your code and prompts never leave your machine. At search time, only the query and library name are sent to Docfork — queries are not stored. Indexed documentation content lives in an upstream vector store; private library content is end-to-end encrypted and deleted atomically when you remove the library. Security →

What libraries are supported? Docfork maintains a curated catalog of popular frameworks. Add any public or private GitHub repository as a custom library. Add custom libraries →

Docs

Community

Star History

Star History Chart

License

MIT

Related MCP servers

Cloud browser automation for LLMs, powered by Browserbase and Stagehand.

3.4k
TypeScript
Apache-2.0
View repository →

Give AI agents full Brave Search capabilities: web, local, image, video, news, place search, LLM context, and summarization.

1.3k
TypeScript
MIT
View repository →

Give AI assistants full control of Unreal Engine—assets, actors, levels, VFX, AI, and cinematics.

763
C++
MIT
View repository →

AI-powered Unreal Engine control via MCP—automate assets, actors, levels, and effects through native C++ automation.

763
C++
MIT
View repository →

Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…

89
Python
Apache-2.0
View repository →

Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…

85
Python
MIT
View repository →