Mintlify
An MCP server that enables users to query any Mintlify-powered documentation site directly from Claude. It leverages Mintlify's AI Assistant API to provide RAG-based answers and code examples for various platforms like Agno, Resend, and Upstash.
What is Mintlify?
Mintlify is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables users to query any mintlify-powered documentation site directly from claude. it leverages mintlify's ai assistant api to provide rag-based answers and code examples for various...
An MCP server that enables users to query any Mintlify-powered documentation site directly from Claude. It leverages Mintlify's AI Assistant API to provide RAG-based answers and code examples for various platforms like Agno, Resend, and Upstash.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that enables users to query any Mintlify-power
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mintlifyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Mintlify
Docmole is an MCP server that lets you query any Mintlify-powered documentation site directly from your AI assistant using retrieval-augmented generation. It supports two modes: a zero-setup Mintlify proxy for pre-configured sites like Agno, Resend, and Upstash, and a local RAG mode where you index any documentation URL yourself using LanceDB for vector search. Developers use it to get accurate, context-aware answers and code examples from official docs without leaving their workflow.
Prerequisites
- Bun runtime installed (https://bun.sh) — required to run bunx/docmole
- OpenAI API key (only required for local RAG mode, not Mintlify proxy mode)
- An MCP client such as Claude Desktop or Claude Code
- A documentation site URL (for local RAG mode) or use a pre-configured Mintlify project slug
Install Bun runtime
Docmole requires the Bun JavaScript runtime. Install it if you don't already have it.
curl -fsSL https://bun.sh/install | bashTest docmole in Mintlify proxy mode
Run docmole with a pre-configured Mintlify project slug to verify it works without any API key. Supported slugs include: agno-v2, resend, mintlify, vercel, upstash, plain.
bunx docmole -p agno-v2Index custom documentation (local RAG mode)
To query any documentation site, set up a local RAG project by providing the URL and a project ID. This requires your OpenAI API key for embeddings.
export OPENAI_API_KEY=your-openai-api-key
bunx docmole setup --url https://docs.yoursite.com --id my-docsServe the local RAG project
Once indexed, start the MCP server for your custom documentation project. Project data is stored in ~/.docmole/projects/<project-id>/.
bunx docmole serve --project my-docsConfigure your MCP client
Add docmole to your Claude Desktop or other MCP client configuration file. Use the Mintlify proxy mode for pre-configured sites or local RAG mode for custom docs.
Mintlify Examples
Client configuration (Mintlify proxy mode)
Claude Desktop config for querying Agno documentation via the Mintlify proxy — no API key needed.
{
"mcpServers": {
"docmole": {
"command": "bunx",
"args": ["docmole", "-p", "agno-v2"]
}
}
}Client configuration (local RAG mode)
Claude Desktop config for querying a custom documentation site indexed locally.
{
"mcpServers": {
"docmole": {
"command": "bunx",
"args": ["docmole", "serve", "--project", "my-docs"],
"env": {
"OPENAI_API_KEY": "your-openai-api-key",
"DOCMOLE_DATA_DIR": "~/.docmole"
}
}
}
}Prompts to try
Example prompts for querying documentation through Docmole.
- "How do I create a new agent in Agno?"
- "Show me a code example for sending an email with Resend"
- "What are the rate limits for the Upstash Redis API?"
- "How do I set up authentication in my Mintlify docs site?"Troubleshooting Mintlify
bunx docmole command not found or fails
Ensure Bun is installed and on your PATH by running 'bun --version'. If missing, install from https://bun.sh and restart your terminal.
Local RAG mode fails with embedding error
Verify your OPENAI_API_KEY environment variable is set correctly and your OpenAI account has active credits. The key is only needed for local RAG mode, not Mintlify proxy mode.
Documentation site not indexing properly in local RAG mode
Ensure the documentation URL is publicly accessible and not behind authentication. Run 'bunx docmole setup --url <url> --id <id>' again to re-index, then restart the server.
Frequently Asked Questions about Mintlify
What is Mintlify?
Mintlify is a Model Context Protocol (MCP) server that mcp server that enables users to query any mintlify-powered documentation site directly from claude. it leverages mintlify's ai assistant api to provide rag-based answers and code examples for various platforms like agno, resend, and upstash. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Mintlify?
Follow the installation instructions on the Mintlify GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Mintlify?
Mintlify works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Mintlify free to use?
Yes, Mintlify is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Mintlify Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Mintlify? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Mintlify in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Mintlify?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.