For the complete documentation index, see llms.txt. This page is also available as Markdown.

MCP Integration

RootCause exposes its tools over the Model Context Protocol (MCP), so AI clients like Claude Code, Claude Desktop, and Cursor can query your data, inspect ontology, and run simulations conversationally. Setup instructions with your platform's real URLs are on the API page, in the MCP Integration section (see API Access).

There are two connection methods. The recommended path is a remote OAuth connection: clients register themselves automatically and you sign in through your browser. No API key to copy or leak. The client sees only the tools its scopes allow, and destructive or long-running actions ask for confirmation before they run; platform procedures — building a twin, composing a causal dataset — arrive as slash commands in clients that support prompts.


With the OAuth method, the config contains no secrets. Authorization happens in your browser, tokens are stored by the client, and access is scoped to the organization or workspace you approve. Every client you authorize appears in the Connected Apps section of the API page, where you can revoke it at any time — revoking deletes the grant and kills its refresh tokens immediately, so the app has to sign in again.

The MCP Integration section of the API page on the OAuth method with the Claude Code tab selected: three setup steps, a terminal command reading claude mcp add --transport http rootcause followed by the platform MCP URL, and a note that no secrets are stored
The MCP Integration section generates the setup for each client with your platform's real URL — here the one-command Claude Code path.

Claude Code

Claude Code is the quickest path: one command, no config file to edit, and it speaks HTTP to the server directly instead of running a local proxy.

  1. Open a terminal and run:

  2. Type /mcp in the chat panel and authenticate: a browser window opens to sign in and authorize.

  3. Pick the organization or workspace to grant. The same /mcp dialog also enables, disables, and reconnects servers later.

Cursor

  1. Open Cursor Settings → MCP, or add to your project's .cursor/mcp.json.

  2. Paste the config:

  3. Cursor prompts you to authenticate: a browser window opens to sign in and authorize.

  4. Pick the organization or workspace to grant, and the RootCause tools appear in Agent mode.

Claude Desktop

  1. Open your Claude Desktop config file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

  2. Paste the config. It uses mcp-remote, which bridges Claude to the remote server and runs the OAuth sign-in for you (this requires Node.js, since the bridge runs via npx):

  3. Restart Claude Desktop. A browser window opens the first time to authorize.


API key connection (legacy)

The legacy method runs the @rootcause/rootcause-mcp stdio bridge locally, authenticated by a static API key. On the API page, select one of your keys in the MCP Integration section and it generates the connection config for you.

Org-wide keys are recommended for this method, so the assistant can list and switch between workspaces; if the integration only ever needs one workspace, scope the key to it instead. See API Access for creating keys.

Prefer the OAuth method for new setups: it avoids storing a long-lived secret in a config file.

Last updated