Roam Research MCP Server

What is Roam Research MCP Server?

It is an MCP server and standalone CLI for interacting with Roam Research graphs. It gives AI agents like Claude read, write, and organize access to notes, while also providing a terminal‑based CLI for direct graph interaction.

How to use Roam Research MCP Server?

Install globally via npm install -g roam-research-mcp. Configure environment variables (ROAM_API_TOKEN, ROAM_GRAPH_NAME for a single graph, or ROAM_GRAPHS for multiple graphs). Run the server with npx roam-research-mcp or use the roam CLI for terminal commands. For AI assistants, add the server to MCP settings with the appropriate command and environment variables.

Key features of Roam Research MCP Server

• Multi‑graph support with optional write protection per graph.
• 20+ MCP tools for fetching, searching, creating, and updating content.
• Standalone CLI with nine commands: get, search, save, refs, update, batch, rename, status, server.
• Stdin piping for all content creation and retrieval commands.
• HTTP Stream transport with a health endpoint and optional bearer authentication.
• Shared server mode (HTTP‑only daemon) for multiple MCP clients.
• Docker deployment support.
• Datalog query support for advanced filtering.

Use cases of Roam Research MCP Server

• Give Claude Code superpowers over your Roam knowledge base.
• Automate note‑taking by piping content from files to Roam daily pages.
• Search and retrieve graph data programmatically via the CLI.
• Manage multiple Roam graphs (e.g., personal, work) with separate tokens.
• Run a long‑lived shared MCP server for multiple AI assistants.

FAQ from Roam Research MCP Server

What is the difference between HTTP_AUTH_TOKEN and ROAM_SYSTEM_WRITE_KEY?

HTTP_AUTH_TOKEN authenticates who may connect to the server (all requests). ROAM_SYSTEM_WRITE_KEY authorizes write operations on protected graphs only;