Add plugin MCP server for Mattermost Agents - #34
Conversation
|
Warning Review limit reached
Next review available in: 46 minutes You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (16)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
322b0ba to
236601e
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 322b0bab1b
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| if err != nil { | ||
| return cursorToolError(response, err), listAgentsOutput{}, nil | ||
| } | ||
| hydrated := p.hydrateAgents(ctx, cacheIdentity, client, list.Items, false) |
There was a problem hiding this comment.
Report the latest run status from list_agents
Passing false here skips run hydration, after which the tool exports agent.Status. Cursor distinguishes the agent resource status from its latest run status—the added test data itself has an ACTIVE agent whose run is FINISHED—so list_agents reports completed work as ACTIVE, unlike create_agent and get_agent, which return run statuses. This prevents callers from reliably identifying completed or failed tasks from the list.
Useful? React with 👍 / 👎.
| if p.httpClient == nil { | ||
| p.httpClient = http.DefaultClient |
There was a problem hiding this comment.
Bound outbound Cursor API requests
When Cursor accepts a connection but stalls before returning headers or a complete body, using http.DefaultClient leaves the MCP tool call without any client-side timeout; if the caller keeps the request open and its context has no deadline, the invocation can hang indefinitely. The removed client previously imposed a 30-second timeout, so activation should install a dedicated client with a bounded timeout rather than the unbounded default.
Useful? React with 👍 / 👎.
236601e to
4306231
Compare
Expose Cursor Cloud Agents tools to the Agents plugin via MCP, using an admin-configured service account API key. Shared cursorapi client and hydration cache land here for the MCP tools. Co-authored-by: Cursor <cursoragent@cursor.com>
4306231 to
6ec5706
Compare
Summary
/mcp) exposing Cursor Cloud Agents tools:create_agent,get_agent,list_agents,add_followup,get_agent_conversation.cursorapiclient + hydration cache; updatesplugin.json, Go 1.26, andmin_server_versionto 11.3.0.Testing
go test ./server/...Release Note