Node Mantis
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DO_NOT_TRACK | No | Set to 1 to opt out of startup error reports. | |
| NODEMANTIS_API_KEY | Yes | Your Node Mantis API key from the dashboard. | |
| NODEMANTIS_TELEMETRY | No | Set to 0 to opt out of startup error reports. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Node Mantis carries out tasks on websites in a real browser and returns the result as structured data. Use run_task for anything that needs clicking, typing or moving between pages, and retrieve_data to read data from one page. Both answer directly when the work finishes quickly. Otherwise they return status "running" with a task_id: call get_task with that id until the status is succeeded, failed or cancelled. Pass result_schema (a JSON Schema) to get the data in a fixed shape. Never put a password or other private value in a goal. Ask the user to set NODEMANTIS_SECRET_ in this server's environment, pass the name in secrets, and refer to it in the goal as secret:NAME.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_taskA | 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. |
| retrieve_dataA | 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. |
| get_taskA | 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. |
| cancel_taskA | Stop a running task and close its browser. A task that already finished is left unchanged. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.