MCP Integration

Sirchmunk provides a Model Context Protocol (MCP) server that exposes its intelligent search capabilities as MCP tools. This enables seamless integration with AI assistants like Claude Desktop and Cursor IDE.

Quick Start

# Install with MCP support
pip install "sirchmunk[mcp]"

# Initialize (generates .env and mcp_config.json)
sirchmunk init

# Edit ~/.sirchmunk/.env with your LLM API key

# Test with MCP Inspector
npx @modelcontextprotocol/inspector sirchmunk mcp serve

Configuration

After running sirchmunk init, a mcp_config.json is generated at ~/.sirchmunk/mcp_config.json. Copy it to your MCP client configuration:

{
  "mcpServers": {
    "sirchmunk": {
      "command": "sirchmunk",
      "args": ["mcp", "serve"],
      "env": {
        "SIRCHMUNK_SEARCH_PATHS": "/path/to/your_docs,/another/path"
      }
    }
  }
}

Transport Modes

stdio (Default)

For local integration with desktop AI tools:

sirchmunk mcp serve

HTTP

For remote or networked scenarios:

sirchmunk mcp serve --transport http --port 3000

Available MCP Tools

sirchmunk_search

Execute an intelligent search query.

Parameters:

• query (string, required) — The search question
• paths (string[], optional) — Directories to search (defaults to SIRCHMUNK_SEARCH_PATHS)
• mode (string, optional) — DEEP or FILENAME_ONLY

sirchmunk_get_cluster

Retrieve a specific knowledge cluster by ID.

Parameters:

• cluster_id (string, required) — The cluster identifier

sirchmunk_list_clusters

List all stored knowledge clusters.

Search Modes

Integration with Claude Desktop

1. Install Sirchmunk with MCP support: pip install "sirchmunk[mcp]"
2. Run sirchmunk init to generate configuration
3. Copy mcp_config.json to Claude Desktop’s MCP config directory
4. Restart Claude Desktop
5. Sirchmunk search tools will appear in Claude’s tool list

Integration with Cursor IDE

1. Install Sirchmunk with MCP support
2. Run sirchmunk init
3. Add the MCP server configuration to Cursor’s settings
4. Sirchmunk becomes available as a tool in Cursor’s AI chat