Skip to content
MCP server

Monito

Browser testing MCP server that lets AI assistants check web apps and read verdicts

Answers · sign-in required (OAuth)

The server answered 3 hours ago with a sign-in request for OAuth (HTTP 401), so we could not list its tools.

Install
Pricing
Freemium
Platforms
API, CLI, Web
Runs
Remotely
Access
Needs sign-in (OAuth)
Version
1.0.0
Listing updated
today

Similar MCP servers

About Monito

Monito is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

Monito's MCP server lets an assistant such as Claude, Cursor or ChatGPT send a URL and an expected outcome to Monito, which runs the check in a real browser in the cloud. The result comes back as passed, failed or unable to verify, with the cause when available, a report link and the first failing step, so the assistant can read the evidence and attempt a fix.

The hosted endpoint works with deployed URLs and needs no local install; a local server, run through the Monito CLI with Node.js 20+, adds localhost checks through a built-in tunnel and CI setup tools. Checks can be saved as reusable tests, and the server also exposes tools for listing projects, scenarios and runs, and for fetching screenshots.

The server is aimed at developers and small teams who want to verify a change in the browser without writing test scripts by hand. Every run consumes credits from the Monito account, and the pricing page lists a free monthly allowance.

Install

Run in a terminal

claude mcp add --transport http monito https://www.monito.dev/api/mcp

Add to Settings → Connectors → Add custom connector

https://www.monito.dev/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "monito": {
      "url": "https://www.monito.dev/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "monito": {
      "type": "http",
      "url": "https://www.monito.dev/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "monito": {
      "serverUrl": "https://www.monito.dev/api/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://www.monito.dev/api/mcp

Enter a Name (for example "Monito"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for OAuth sign-in. If its docs give you an OAuth client ID and secret, enter them in the form's OAuth Client ID and Client Secret fields.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "monito": {
      "type": "http",
      "url": "https://www.monito.dev/api/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (10)

Taken from the project documentation; the running server may differ.

check
Runs a URL and expected outcome in a real browser and returns a verdict.
save_check
Saves a check as a reusable named test.
get_run
Returns the evidence for a run.
get_screenshot
Returns one screenshot named in run evidence.
wait_for_run
Resumes waiting for a run that has not finished.
list_projects
Lists the user's projects.
list_scenarios
Lists saved scenarios.
list_runs
Lists recent runs.
run_scenario
Runs a saved scenario.
run_project
Runs the newest saved scenarios in a project.

What it does

Plain-English browser checks
Describe a URL and the expected behaviour, and Monito runs it in a real browser and returns a verdict.
Evidence-backed verdicts
Failed runs return evidence such as screenshots, network and console data for the agent to diagnose.
Hosted or local connection
A hosted endpoint works with deployed URLs, while a local server adds localhost checks via a tunnel.
Saveable reusable tests
A successful or failed check can be saved with a name and later run as a scenario or suite.
Retry-safe run launches
A request ID stops a retried call from starting or charging for the same run twice.

Good for

  • Confirm a checkout or signup flow still works after an AI-assisted code change
  • Check a staging or preview deployment in a real browser before release
  • Have an assistant reproduce a reported bug and read the evidence to fix it
  • Turn an ad hoc browser check into a saved test for later runs

Pricing

Freemium, from $79 a month

Free plan with 50 test credits a month; Pro from $79/mo; Team $199/mo.

Prices change. Check monito.dev before you buy.

Monito FAQ

Can the hosted server check localhost URLs?

No. The hosted server at /api/mcp rejects localhost and private-network URLs and expects a deployed preview; localhost checks need the local server.

What does a check cost?

A test run costs 1 credit and Discovery costs 20. The free plan includes 50 test credits each month.

Which AI clients are supported?

The docs list Claude (web and desktop), ChatGPT, Claude Code, Cursor and VS Code for the hosted server, with Codex also supported by the local server.

Is Monito free?

Monito has a free plan, with paid plans for more usage or features. Paid plans start at $79 a month.

How do I add Monito to Claude Code?

Run this command in your terminal: claude mcp add --transport http monito https://www.monito.dev/api/mcp

What are the best alternatives to Monito?

The closest alternatives to Monito are MCP Server, M00N Report, Testsy, Testiny Test Management and Netmon (demo).

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Status: checked automatically by AIPoweredBot on 19 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers