Use Comma with JetBrains AI Assistant

AI Assistant runs the same way across IntelliJ IDEA, PyCharm, WebStorm, GoLand and Rider, and it speaks MCP. Its remote-server form takes a URL but no documented header field — so for Comma, which authenticates with a Bearer token, bridge through mcp-remote.

Add Comma to JetBrains AI Assistant

Settings → Tools → AI Assistant → Model Context Protocol (MCP) → Add. Paste the JSON and choose whether the server is global or project-level.

{
  "mcpServers": {
    "comma": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://commareports.com/api/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}",
        "--transport",
        "http-only"
      ],
      "env": { "AUTH_HEADER": "Bearer comma_sk_…" }
    }
  }
}

Replace comma_sk_… with a token from Settings → API tokens → New token on Comma (or export it as COMMA_API_TOKEN where the snippet reads an env var). The default scopes — reports:write, comments:read, comments:write — cover publishing and review.

Requires Node.js on the machine — npx fetches mcp-remote the first time the IDE starts the server.

JetBrains AI Assistant gotchas

  • Why the bridge: AI Assistant's remote form is {"url": …} only. mcp-remote runs locally over stdio and adds your header to every HTTP call to Comma.
  • No spaces around the colon in Authorization:${AUTH_HEADER} — some IDEs split args on whitespace. The space after Bearer lives in the env value, where it's safe.
  • Using Junie instead? It reads headers natively — see the Junie guide.

What the agent can do

Capability Tools
Publish a report create_report, update_report, create_report_from_url
Find existing reports list_reports, search_reports, get_report, read_report
Leave / reply to comments add_comment, reply_to_comment, set_comment_status, list_comments
Ask for review, share request_review, set_report_sharing, get_report_signoffs
Manage assets upload_report_asset, list_report_assets, delete_report_asset

AI Assistant picks the tool from the request — there are no JetBrains AI Assistant-specific commands to learn.

A workflow that sticks

  1. Ask AI Assistant to write up the work as a self-contained HTML report and publish it to Comma. It calls create_report and returns a link.
  2. Send the link. Reviewers open a rendered page and leave comments anchored to the exact line, cell or chart they mean — no account needed to read a public link.
  3. Next session, ask AI Assistant to address the comments. It reads the threads with list_comments, ships a revision with update_report (same URL), replies, and resolves them.

Reports belong to your workspace, not to the agent. A report published from JetBrains AI Assistant can be revised tomorrow from Claude Code or Cursor, and the link people bookmarked keeps working.

Token shape

  • Lives in the env block of the IDE's MCP settings — choose global rather than project level so it isn't shared through .idea.
  • Scoped — you choose which actions it can take when you create it.
  • Revocable in one click from Settings → API tokens; revocation applies immediately to the REST API, the MCP server and any routines the token created.
  • Rate-limited per token.

Details in API tokens → and Scoped tokens for AI agents →.

Try it

Add the entry, generate a token, restart JetBrains AI Assistant, and ask for a report on something you worked on today. Then leave a comment on it and ask the agent what it sees.

Generate a token →

Related