--- title: "How to Set Up the Momentic MCP Server in Claude Code, Cursor, and Codex" description: "The commands for each client, the API key mistake that breaks most setups, and how to confirm your agent really has the Momentic tools." canonical: "https://momentic.ai/blog/how-to-set-up-momentic-mcp-server" last-updated: "2026-09-01T20:54:01Z" --- # How to Set Up the Momentic MCP Server in Claude Code, Cursor, and Codex URL: https://momentic.ai/blog/how-to-set-up-momentic-mcp-server [blog](/blog) [/ resources](/blog/category/resources) / how-to-set-up-momentic-mcp-server Resources The commands for each client, the API key mistake that breaks most setups, and how to confirm your agent really has the Momentic tools. Wei-Wei Wu CEO, Momentic A coding agent can write a test in seconds and still leave you with a suite nobody can read. The Momentic MCP server changes what the agent has in its hands: a live browser, your existing tests, and the run history behind them. This guide connects that server to Claude Code, Cursor, and Codex, then shows how to confirm the connection works. ## What you get Momentic's MCP server is a local stdio server. It runs on your machine, next to your repository, and it exposes tools that let an agent do four things: - Read and edit the tests already in your repository - Drive a live browser, step by step, and see a screenshot after each step - Run a test or a range of steps and read the result - Read run history, so it can explain why a test failed on a branch A test is a YAML file in your repository, so every change the agent makes arrives as a diff you review in a pull request. ## Before you start - The Momentic CLI, version 2.54.0 or later - `momentic.config.yaml` in your project - A `MOMENTIC_API_KEY` the MCP process can read. Most editors do not inherit your shell environment, so set the key in the editor config. Sign in once from your project root: `npx momentic login` Every client below runs the same command underneath: `npx momentic mcp --config /absolute/path/to/momentic.config.yaml` For Android and iOS, substitute `momentic-mobile mcp` and sign in with `npx momentic-mobile login`. ## Claude Code Register the server from your project root: `claude mcp add --transport stdio momentic -- npx momentic mcp --config /absolute/path/to/momentic.config.yaml` Pass the API key with the CLI's `--env` flag, or run the command from a shell that already exports it. On native Windows, wrap the command with `cmd /c`. Restart Claude Code, then run `/mcp` to see the server. ## Cursor Open the command palette, select **View: Open MCP Settings**, click **Add a new Custom MCP server**, and paste this entry: `{ "mcpServers": { "momentic": { "type": "stdio", "command": "npx", "args": [ "momentic", "mcp", "--config", "/absolute/path/to/momentic.config.yaml" ], "env": { "MOMENTIC_API_KEY": "your-api-key" } } } }` Restart Cursor after you save the file. ## Codex Register the server: `codex mcp add momentic -- npx momentic mcp --config /absolute/path/to/momentic.config.yaml` The command writes the entry to `~/.codex/config.toml`. For a project-scoped config, edit `.codex/config.toml` in a trusted project. Restart Codex, then run `/mcp` in the TUI. ## Other clients Any MCP-compatible client can launch the server. VS Code with Copilot, OpenCode, and Devin all work. Give the client these three values: - Command: `npx` - Arguments: `momentic mcp --config /absolute/path/to/momentic.config.yaml` - Environment: `MOMENTIC_API_KEY=your-api-key` Devin needs a few extra machine-configuration steps, because it installs browsers and skills before MCP starts. The [Devin integration page](https://momentic.ai/docs/integrations/devin) covers them. ## Install the skills The server gives the agent tools. The skills tell it how to use them, and this is the part teams skip. Without the skills, an agent writes malformed steps and then argues with the error. Install them from your project root: `npx skills add momentic-ai/skills` Three skills matter: - `momentic-test`: how to build tests, steps, and modules that hold up - `momentic-spec`: how to write the affected tests before you change product code - `momentic-maintain`: how to investigate a branch failure, deflake a test, and repair a stale step Some agents load skills on their own. Many do not, so name the skill in the prompt: `/momentic-test write a test for the checkout flow` ## Confirm it works Restart the client and start a new chat. Ask the agent which MCP tools it has. You want to see `momentic_*` tools, such as `momentic_get_artifacts`. If they do not appear, quit the client fully and open it again; a reload is often not enough. Then give the agent a real job and read the diff: `/momentic-test open the login page, sign in with the seeded test user, and assert the dashboard loads` The agent drives the browser, checks each step against a screenshot, and leaves a YAML test in your repository. Run it yourself before you commit it: `npx momentic run tests/login.yaml` ## Two things that break setups The missing API key. The editor starts the server, the server cannot authenticate, and the agent reports a vague failure. Put `MOMENTIC_API_KEY` in the client config, not only in your shell. The leaked browser. The agent closes a session with `momentic_session_terminate`. If you hard-stop the editor mid-run, browser processes stay alive. Also add `.momentic-mcp/` to your gitignore, because screenshots, videos, and traces land there. ## Where this leaves your suite The point of the MCP server is not that an agent can click a button. It is that the tests it writes go into your repository, run in your CI, and get reviewed like code. The agent proposes; you merge. If you are weighing this against a browser-only server, read [Playwright MCP vs a testing MCP server](https://momentic.ai/blog/playwright-mcp-vs-testing-mcp-server). If flaky tests are what sent you here, start with [how to fix flaky tests](https://momentic.ai/blog/how-to-fix-flaky-tests). ## Momentic MCP setup, answered. What is the Momentic MCP server? It is a local stdio server that gives a coding agent tools to read and edit the Momentic tests in your repository, drive a live browser step by step, run tests, and read run history. It runs on your machine with npx momentic mcp --config /absolute/path/to/momentic.config.yaml. Which coding agents can connect to it? Any MCP-compatible client. Claude Code, Cursor, and Codex have one-line or one-file setups. VS Code with Copilot, OpenCode, and Devin work with the same command, arguments, and API key. Why does the agent say it has no Momentic tools? Two usual causes. The client was reloaded instead of fully restarted, or the MOMENTIC_API_KEY is only in your shell. Most editors do not inherit your shell environment, so set the key in the client config and restart the client. Do I need the skills as well as the server? You want both. The server supplies the tools; the skills supply the operating guidance that keeps an agent on Momentic's test format. Install them with npx skills add momentic-ai/skills, then name the skill in your prompt, such as /momentic-test. Where do the tests the agent writes end up? In your repository, as YAML files. You review them in a pull request and run them locally or in CI with npx momentic run. Nothing is hidden in a vendor dashboard. Does it work for mobile apps? Yes. Substitute momentic-mobile mcp for the web command, sign in with npx momentic-mobile login, and use the momentic-mobile-test skill for Android and iOS. Still have additional questions? ## Keep reading. [Resources Best Puppeteer Alternatives for Browser Automation Compare the best Puppeteer alternatives for browser automation, E2E testing, and web scraping. Explore Playwright, Selenium, Cypress, Momentic, and more. Wei-Wei Wu 8 min read](/blog/puppeteer-alternatives)[Resources Best Qodex Alternatives for UI Testing Compare the best Qodex alternatives for UI testing, including Momentic, QA Wolf, mabl, Testim, and more. Explore AI-powered testing, self-healing locators, and web and mobile support. Wei-Wei Wu 8 min read](/blog/qodex-alternatives)[Resources Best Shiplight Alternatives for AI-Native Testing Compare the best Shiplight alternatives for AI-native testing, including Momentic, Playwright, mabl, TestRigor, and QA Wolf. Explore self-healing, autonomous testing, mobile support, and more. Wei-Wei Wu 7 min read](/blog/shiplight-alternatives) ## Close the feedback loop. Point Momentic at your app. Free to start, no credit card. [Try for free](https://app.momentic.ai/signup) [Contact sales](/sales)