Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "human-ai": {
      "type": "http",
      "url": "https://human-api-labs.onrender.com/mcp"
    }
  }
}

claude mcp add --transport http human-ai https://human-api-labs.onrender.com/mcp

[mcp_servers.human-ai]
url = "https://human-api-labs.onrender.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "human-ai": {
      "type": "remote",
      "url": "https://human-api-labs.onrender.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "human-ai": {
      "type": "http",
      "url": "https://human-api-labs.onrender.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=human-ai&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vaHVtYW4tYXBpLWxhYnMub25yZW5kZXIuY29tL21jcCJ9"
}

{
  "servers": {
    "human-ai": {
      "type": "http",
      "url": "https://human-api-labs.onrender.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "human-ai": {
      "httpUrl": "https://human-api-labs.onrender.com/mcp"
    }
  }
}

extensions:
  "human-ai":
    enabled: true
    name: "human-ai"
    type: streamable_http
    uri: "https://human-api-labs.onrender.com/mcp"
    timeout: 300

Quality 68 / 100needs work

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_task_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); request_human_help (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); discover_humans (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 344 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability50 · weight 15

pass
stability.changes2 tool changes in 30 days
fail
stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 344 tokens to load them all · tool set 6448d495bff3 · tools last changed 2026-10-30 · checked 2026-11-07 17:28 UTC

Tool changes

2026-10-30request_human_helpchangeddescriptionmeaning changed
before
Request voluntary help from a human for a real-world task. The human must explicitly accept before the request is considered accepted.
after · 23% of words in common
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.
2026-10-30discover_humanschangeddescription
before
Discover voluntary human capability profiles for real-world tasks requiring physical presence, perception, access, judgment or action.
after · 54% of words in common
Discover voluntary humans for physical-world tasks requiring presence, eyes, hands, inspection, photography, local access, verification, perception or human judgment.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 94 / 100

provenance80

liveness100

freshness100

hygiene100

+repository +namespace-matches-repo +reachable +uptime-100% +updated-8d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://human-api-labs.onrender.com/mcp` streamable-http	none	yes	100%	328 ms	2025-11-25	2026-11-07

Tools (3)

`discover_humans`	Discover voluntary humans for physical-world tasks requiring presence, eyes, hands, inspection, photography, local access, verification, perception or human judgment.
`get_task_status`	Retrieve the current human decision and status for a HUMAN API task.
`request_human_help`	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.human-api-labs/human-ai",
  "title": "HUMAN API",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://human-api-labs.onrender.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.2.1",
  "repository": {
    "url": "https://github.com/human-api-labs/human-ai",
    "source": "github"
  },
  "description": "Human execution API for AI agents needing voluntary help with physical-world tasks."
}