Comma

Use Comma with Augment Code

Augment's context engine is good at the questions that span a whole codebase — which means its answers run long. Attach Comma and a long answer becomes a report with a URL and anchored comments rather than a chat transcript.

Add Comma to Augment Code

~/.augment/settings.json, shared by the Auggie CLI. The IDE extensions also have a remote MCP form under their settings.

{
  "mcpServers": {
    "comma": {
      "type": "http",
      "url": "https://commareports.com/api/mcp",
      "headers": {
        "Authorization": "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.

auggie mcp add comma --transport http --url https://commareports.com/api/mcp --header "Authorization:Bearer comma_sk_…"

Augment Code gotchas

  • Header in the CLI or settings file. Augment's IDE remote-MCP form is documented with a name and URL only; auggie mcp add and settings.json are the documented ways to send a header.
  • Add a rule in .augment/rules/ so Augment publishes long answers to Comma by default.
  • Scope the token to reports:write + comments:read if the agent should read feedback but never post comments.

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

Augment picks the tool from the request — there are no Augment Code-specific commands to learn.

A workflow that sticks

  1. Ask Augment 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 Augment 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 Augment Code can be revised tomorrow from Claude Code or Cursor, and the link people bookmarked keeps working.

Token shape

  • Lives in ~/.augment/settings.json, a user-level file.
  • 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 Augment Code, 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