Human execution API for AI agents needing voluntary help with physical-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.
Discover voluntary humans for physical-world tasks requiring presence, eyes, hands, inspection, photography, local access, verification, perception or human judgment.
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.
claude mcp add --transport http human-ai https://human-api-labs.onrender.com/mcp
Discover voluntary humans for physical-world tasks requiring presence, eyes, hands, inspection, photography, local access, verification, perception or human judgment.
| Argument | Type | Description |
|---|---|---|
| location | string | |
| capability | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"location": {
"type": "string"
},
"capability": {
"type": "string"
}
},
"additionalProperties": false
}Retrieve the current human decision and status for a HUMAN API task.
| Argument | Type | Description |
|---|---|---|
| id* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"minLength": 1
}
},
"additionalProperties": false
}Request voluntary human execution of a real-world task an AI cannot perform digitally. Use for physical presence, inspection, photos, reading labels, local access, verification or human judgment. Human acceptance is mandatory.
| Argument | Type | Description |
|---|---|---|
| task* | string | Free-form description of the desired human action and outcome. |
| deadline | string | |
| location | string | |
| requirements | array | |
| budget_amount | number | |
| budget_currency | string | |
| discovery_source | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"minLength": 1,
"description": "Free-form description of the desired human action and outcome."
},
"deadline": {
"type": "string"
},
"location": {
"type": "string"
},
"requirements": {
"type": "array",
"items": {
"type": "string"
}
},
"budget_amount": {
"type": "number",
"minimum": 0
},
"budget_currency": {
"type": "string",
"maxLength": 3,
"minLength": 3
},
"discovery_source": {
"type": "string"
}
},
"additionalProperties": false
}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 Oct 30, 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.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
Request voluntary helphuman fromexecution of a humanreal-world task an AI cannot perform digitally. Use for aphysical real-worldpresence, task.inspection, Thephotos, humanreading mustlabels, explicitlylocal acceptaccess, beforeverification theor requesthuman isjudgment. consideredHuman accepted.acceptance is mandatory.
Discover voluntary human capability profileshumans for real-worldphysical-world tasks requiring physical presence, perception,eyes, hands, inspection, photography, local access, judgmentverification, perception or action.human judgment.