AI CodeOps for Cursor

Cursor is an AI code editor, with agents that run in the editor and in the cloud. AI CodeOps is a browser-based platform where AI agents plan, write, test and review a change, and the change becomes a pull request only after its quality gates pass and a person approves it. Add the AI CodeOps MCP server to Cursor and the agent in your editor can hand a task to a gated AI CodeOps session, follow it, read its findings and ask whether a pull request may ship.

What AI CodeOps gates, and what it doesn't

AI CodeOps gates the changes made in its own sessions. Cursor's cloud agents work on a separate branch and push changes to your repository for handoff, and can open pull requests (cloud agents). Those are ordinary pull requests: AI CodeOps doesn't review them, and the release check denies them because no AI CodeOps session made them.

To put Cursor's work through the gates, ask the agent in Cursor to start an AI CodeOps session with the task. The session writes the change, runs your tests, reviews it with several agents and opens the pull request only when the gate passes. Or ask the release gate before you merge, from Cursor or from CI.

Connect Cursor

1. In AI CodeOps, create a workspace API key under Configure → API Keys. It starts with sk- and is shown once. To let Cursor start sessions, choose Scope on the key and tick Start sessions from the MCP server (/mcp). See API keys.
2. Put the key in an environment variable, for example AICODEOPS_API_KEY.
3. Add the server to .cursor/mcp.json in your project, or to ~/.cursor/mcp.json to use it everywhere (Cursor MCP docs):

``json { "mcpServers": { "aicodeops": { "url": "https://console.aicodeops.dev/mcp", "headers": { "Authorization": "Bearer ${env:AICODEOPS_API_KEY}" } } } } ``

Cursor resolves ${env:NAME} in the url and headers fields, so the file can be committed without the key in it.

What the agent in Cursor can do

The server has six tools: list_projects, start_session, get_session, check_release_gate, list_findings and get_evidence_pack. Each acts as the key's creator, with their role, the workspace budget and the agent's work-in-progress limit, exactly as in the console. start_session and get_evidence_pack work only for a key whose scope lists their permission. The details are in the MCP server guide.

Things to ask the agent:

Start an AI CodeOps session on the web project: fix the date parsing bug in the invoice export, with a test.
What did the AI CodeOps reviewers find on that session? List anything high or critical.
Does the AI CodeOps release gate allow https://github.com/acme/web/pull/17? Give me the reasons.

A session started from Cursor opens its pull request like any other, so approvals and the release gate still apply before it merges.

Gate merges in CI

The same check is an HTTP API your pipeline can call before a merge, on any CI system that can run curl:

curl -sf -X POST "https://console.aicodeops.dev/api/release/check" \
  -H "Authorization: Bearer $AICODEOPS_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"pullRequestURL\":\"$PR_URL\"}" > gate.json
jq -e '.allowed == true' gate.json

It answers 200 with allowed, a summary and reasons. Options include a coverage floor, required workflows, disallowed licenses and a required staging deployment (API). As a required check, it denies any pull request no AI CodeOps session made.

Limits

• 120 MCP requests a minute from one address.
• Stateless: the server sends no notifications, so the agent polls get_session to follow a session.
• Workspace API keys only. OAuth sign-in isn't supported yet.

Getting started

1. Create a free account: AI CodeOps is in open beta and runs in your browser.
2. Connect your Git host and create a project, using the quickstart.
3. Create an API key and add the server to Cursor as above.

Deciding between the two products rather than combining them? Read AI CodeOps vs Cursor. Using another agent? See AI CodeOps for Claude Code.