gotoHuman MCP Server

@andyciggy

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT license

トランスポート

stdio

作者

andyciggy

gotoHuman MCP Server について

概要はまだありません

#gotohuman#human-approval #ai-workflows

gotoHuman MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "gotohuman-mcp-server-andyciggy": {
      "command": "npx",
      "args": [
        "@gotohuman/mcp-server"
      ]
    }
  }
}

gotoHuman MCP Server のツール

List all available review templates. NOTE: You need to fetch the schema for the template fields first using the get-form-schema tool.

Get the partial schema ('fields' and 'config' (optional) properties) to be used when requesting a human review with the given review template.

Request a human review with a review template. NOTE: If you don't have a review template ID yet, list all available review templates using the list-forms tool first. To know what to pass for fieldData, you need to fetch the schema for the review template fields using the get-form-schema tool. For multi-step workflows, pass workflow with the same runId on each step and prevSteps listing prior reviewIds; use workflowRunId from the response when gotoHuman assigns a new runId.

概要

What is gotoHuman MCP Server?

A fully-managed MCP server that adds human approvals to AI agents and agentic workflows. It provides an async human-in-the-loop workflow with a customizable approval UI, built‑in auth, webhooks, notifications, team features, and an evolving training dataset. It enables requesting human reviews directly from AI workflows or integrating the approval step into an IDE.

How to use gotoHuman MCP Server?

Install via npx @gotohuman/mcp-server and set the GOTOHUMAN_API_KEY environment variable. Configure the server in your MCP client (Cursor, Claude, Windsurf) using the JSON snippet provided. Invoke the three available tools: list-forms, get-form-schema, and request-human-review-with-form.

Key features of gotoHuman MCP Server

Lists all available review forms
Returns the schema for a given form
Requests a human review with form data
Supports optional metadata and user assignment
Provides a link to the review in gotoHuman

Use cases of gotoHuman MCP Server

Adding human approval steps to autonomous AI agents
Enabling human‑in‑the‑loop reviews in background agent workflows
Integrating approval requests directly into IDE assistants
Collecting training data from human decisions on AI outputs

よくある質問

What does this server do and how does it compare to alternatives?

It enables AI agents to request human approvals via MCP, with a managed UI, webhooks, and team features. The README does not compare it to other solutions.

What dependencies or runtime are required?

The server requires Node.js to run, as it is invoked via `npx` (or directly from a built JavaScript bundle).

Where does the data live?

All review forms and submissions are handled on the gotoHuman platform (app.gotohuman.com). No local storage details are provided.

What are the known limits of the server?

The README does not document any rate limits, concurrency limits, or other restrictions.

How is authentication and transport handled?

Authentication uses a `GOTOHUMAN_API_KEY` environment variable. Communication is over standard MCP transport.

「その他」の他のコンテンツ

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi