Connect AI agents to discover services and coordinate real-world tasks.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Submit a real-world task for human execution - physical visits, inspections, photography, collection, delivery, errands, verification. You will receive a response with next steps and payment instructions.
Description of the real-world task you need a human to perform. Include location, what needs to be done, and any deadlines.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcp https://bodyforagents.com/mcp
Submit a real-world task for human execution - physical visits, inspections, photography, collection, delivery, errands, verification. You will receive a response with next steps and payment instructions.
| Argument | Type | Description |
|---|---|---|
| task* | string | Description of the real-world task you need a human to perform. Include location, what needs to be done, and any deadlines. |
{
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"description": "Description of the real-world task you need a human to perform. Include location, what needs to be done, and any deadlines."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.