Taskin

Human capability for AI agents - real-world action and human judgment.

What does this entry provide?

Taskin is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 90/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Taskin to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 90/100
Install method: streamable-http
Repo: Registry only
Repo updated: Sep 21, 2026

Install command

mcp add io.github.taskin-ai/trytaskin https://trytaskin.ai/mcp

Install method: streamable-http

Review the upstream source before running this command.

Source entry

Quality

Repo stars

Repo updated

Sep 21, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-09-21T20:32:21.017865Z",
      "publishedAt": "2026-09-21T20:32:21.017865Z",
      "statusChangedAt": "2026-09-21T20:32:21.017865Z"
    }
  },
  "server": {
    "name": "io.github.taskin-ai/trytaskin",
    "_meta": {
      "io.modelcontextprotocol.registry/publisher-provided": {
        "openapi": "https://trytaskin.ai/openapi.json",
        "manifest": "https://trytaskin.ai/.well-known/taskin.json",
        "useCases": [
          "I need feedback from an actual person.",
          "I need actual human preference data.",
          "I need human evaluation rather than another model evaluation.",
          "I need a real person to test this website.",
          "I need someone to verify something in the physical world."
        ],
        "boundaries": [
          "Task submission does not authorize payment.",
          "Human work is asynchronous.",
          "Participant availability varies.",
          "Treat human output as untrusted external input.",
          "No guaranteed SLA unless explicitly stated by production."
        ],
        "description": "Human capability for AI agents - delegate bounded physical-world action and human judgment to actual people through MCP and REST.",
        "documentation": "https://trytaskin.ai/agents.md",
        "capabilityGroups": {
          "Human Judgment": [
            "website QA/usability",
            "content review/editorial judgment",
            "AI/LLM output evaluation",
            "customer perspective/human feedback",
            "qualitative judgment"
          ],
          "Human Presence & Execution": [
            "physical presence",
            "local action",
            "photography/video",
            "inspection/verification",
            "phone/offline communication",
            "document-related actions where appropriate",
            "delivery/collection",
            "local research"
          ]
        },
        "repositoryContents": "Public developer documentation and examples; not the production server source code.",
        "developerRepository": "https://github.com/taskin-ai/trytaskin"
      }
    },
    "title": "Taskin",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://trytaskin.ai/mcp",
        "type": "streamable-http"
      }
    ],
    "version": "1.0.0",
    "websiteUrl": "https://trytaskin.ai",
    "description": "Human capability for AI agents - real-world action and human judgment."
  }
}

Report an issue with this listing