Node Mantis
OfficialNode Mantis MCP server
This MCP server connects your AI assistant to Node Mantis browser automation. Give Node Mantis a task in natural language, and it carries it out in a real browser, acting like a person: clicking buttons, filling forms, and interacting with complex widgets the way a person would. It can also read data from pages and return structured results.
Connect your assistant
You need a Node Mantis API key from the dashboard and Node.js or Python. The server is included in the node-mantis package on npm and PyPI.
Add this entry to your assistant's MCP settings, replacing the API key placeholder:
{
"mcpServers": {
"node-mantis": {
"command": "npx",
"args": ["-y", "node-mantis", "mcp"],
"env": {
"NODEMANTIS_API_KEY": "<your-node-mantis-api-key>"
}
}
}
}For Python with uv, use "command": "uvx" and "args": ["node-mantis", "mcp"] instead. Keep the same API key setting.
Your assistant starts the server for you. Save the settings and restart your assistant. The setup guide has installation requirements and instructions for individual assistants.
Related MCP server: Cloudflare Playwright MCP
Try it on the sandbox
The Node Mantis sandbox is a demo bookshop where you can try website tasks.
Add a book to the bag
Ask your assistant:
Use Node Mantis to open https://sandbox.nodemantis.com. Open Travel & Adventure, add one copy of Journey to the Center of the Earth to the bag, then open the bag and report the book's title and quantity.
The corresponding run_task inputs are:
{
"goal": "Open Travel & Adventure, add one copy of Journey to the Center of the Earth to the bag, then open the bag and report the book's title and quantity.",
"start_url": "https://sandbox.nodemantis.com"
}Read a book's details
Ask your assistant:
Use Node Mantis to read the title, author, and displayed price from https://sandbox.nodemantis.com/books/journey-to-the-center-of-the-earth without interacting with the page.
The corresponding retrieve_data inputs are:
{
"url": "https://sandbox.nodemantis.com/books/journey-to-the-center-of-the-earth",
"prompt": "Read the book's title, author, and displayed price."
}Tools
Tool | What it does |
| Carries out a website task from a natural-language goal. Supports an optional starting URL, result schema, effort setting, cost and step limits, and timeout. |
| Reads data from one page without interacting with it. Use |
| Checks a task's progress and collects its result. |
| Stops a running task. |
For results in a particular format, pass result_schema, a JSON Schema describing the fields you want. See the tool reference for all inputs.
Calls wait up to 45 seconds by default. If the task takes longer, it keeps running and returns a task_id. Your assistant uses get_task to check back or cancel_task to stop it.
Error reports
Node Mantis collects startup error reports by default to help improve the product. Reports can include an error type and filtered message, app version, operating system, installation method, and a random installation ID.
To opt out, set NODEMANTIS_TELEMETRY=0 or DO_NOT_TRACK=1 in your MCP server's environment.
Source and licence
This repository contains the Python and TypeScript source for the MCP server. To run the source or contribute changes, see CONTRIBUTING.md.
The MCP code is licensed under MIT. The separately installed Node Mantis client and other Node Mantis software and services keep their own licences.
For an MCP problem or request, open an issue with your client version and an example with private data removed. More help and the full reference are at nodemantis.com/docs/mcp.
Available Tools
4 toolscancel_taskCancel a taskAIdempotent
Stop a running task and close its browser. A task that already finished is left unchanged.
Inputs: task_id (required).
get_taskCheck a taskARead-onlyIdempotent
Wait for a task started by run_task or retrieve_data and return its status, latest progress and, once finished, its result. Returns as soon as the task finishes, or after wait_seconds with status "running" (call again). Tasks are kept for an hour after they finish and are lost when this server restarts.
Inputs: task_id (required), wait_seconds.
retrieve_dataRead data from a pageARead-onlyIdempotent
Open one page and read data from it without changing anything on it. Returns the data, shaped by result_schema when given. Use run_task instead when getting to the data takes clicking, typing or several pages. If reading is still going when the call returns, the reply has status "running" and a task_id: call get_task with it.
Inputs: url (required), prompt (required), effort, use_proxy, +2 more.
run_taskRun a website taskADestructive
Carry out a task on a website from a plain-English goal: navigate, click, type, fill in forms and read the outcome, in a real browser. Returns the outcome and, when result_schema is given, the data in that shape. If the task is still going when the call returns, the reply has status "running" and a task_id: call get_task with it. Each call starts a fresh browser session with no saved logins.
Inputs: goal (required), effort, secrets, max_steps, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool owns a distinct action in the browser-task lifecycle: start an acting task, start a read-only extraction, wait on a task, and cancel a task. The descriptions explicitly resolve the one risky boundary (run_task vs retrieve_data) by telling the agent to prefer run_task when navigation or multiple pages are needed.
All four names follow a consistent snake_case verb_noun pattern (run_task, retrieve_data, get_task, cancel_task). The shared _task suffix on the task-lifecycle tools reinforces the pattern and makes relationships visible.
Four tools is tight and well-scoped for a browser automation server: two entry points for starting work and two for managing in-flight tasks. Nothing feels redundant or missing at the naming level.
The async lifecycle is fully covered (start, poll, cancel) plus optional result_schema shaping for output. Minor gaps remain: there is no way to list or enumerate outstanding tasks/task_ids, and the absence of session persistence means logins and multi-step flows can never be resumed across calls.
Maintenance
Related MCP Connectors
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
Let your AI agent operate any website through a real, logged-in browser session.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with web browsers using natural language, featuring automated browsing, form filling, vision-based element detection, and structured JSON responses for systematic browser control.63MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.Apache 2.0
- AlicenseAqualityCmaintenanceEnables AI-powered web browsing automation using Google's Gemini 2.5 Computer Use API. Allows agents to navigate websites, click buttons, fill forms, and extract information through natural language commands with real-time progress tracking.7MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI assistants to browse websites, extract information, fill forms, interact with pages, and execute multi-step web tasks autonomously.-