Roam Research MCP Server logo

Roam Research MCP Server

by 2b3pro

A Model Context Protocol (MCP) server that provides comprehensive access to Roam Research's API functionality. This server enables AI assistants like Claude to interact with your Roam Research graph through a standardized interface.

View on GitHub

Last updated: N/A

What is Roam Research MCP Server?

This is a Model Context Protocol (MCP) server designed to provide a standardized interface for AI assistants to interact with Roam Research. It allows AI models like Claude to access and manipulate data within your Roam Research graph.

How to use Roam Research MCP Server?

First, install the server using npm or by cloning the repository and building from source. Then, configure the necessary environment variables (ROAM_API_TOKEN, ROAM_GRAPH_NAME, MEMORIES_TAG) either in a .env file or within your MCP settings. Finally, use the provided use_mcp_tool commands with appropriate parameters to interact with your Roam Research graph.

Key features of Roam Research MCP Server

  • Comprehensive input validation

  • Case-insensitive page title matching

  • Recursive block reference resolution

  • Markdown parsing and conversion

  • Daily page integration

  • Efficient batch operations

  • Hierarchical outline creation

  • Datomic Query Support

Use cases of Roam Research MCP Server

  • Automating data entry and organization in Roam Research

  • Building AI-powered assistants that can access and manipulate your Roam Research graph

  • Creating custom workflows and integrations with other tools

  • Analyzing and visualizing data stored in Roam Research

FAQ from Roam Research MCP Server

What is an MCP server?

A Model Context Protocol (MCP) server provides a standardized interface for AI models to interact with applications.

How do I get a Roam Research API token?

Go to your graph settings in Roam Research, navigate to the 'API tokens' section, and create a new token.

Where do I configure the environment variables?

You can configure the environment variables in a .env file or within your MCP settings file (e.g., cline_mcp_settings.json or claude_desktop_config.json).

What happens if a page or block is not found?

The server provides comprehensive error handling for common scenarios, including 'Page not found' and 'Block not found' errors, with detailed error messages and suggestions for resolution.

How can I test the server?

Use the MCP Inspector tool to test and debug the server. Run npx @modelcontextprotocol/inspector node build/index.js to start the server in inspector mode.