mcpField
G
gotoHuman MCP Server

gotoHuman MCP Server

Local
github.com/gotohumanAI & Agents52Updated 4w ago

About gotoHuman MCP Server

gotoHuman MCP Server lets AI agents and agentic workflows request human approvals. It targets teams that need a human review step, with a customizable approval UI and built-in auth, webhooks and notifications.

Key features

  1. 01Request human reviews from MCP tools
  2. 02List review types available in an account
  3. 03Fetch field schemas for review types
  4. 04Return review results through webhooks
  5. 05Assign reviews to specified user emails

Use cases

  1. 01Approving AI-generated output before release
  2. 02Review steps within multi-step agentic workflows
  3. 03Adding approval steps while integrating in Cursor or Claude

MCP support

This is an MCP server that exposes tools such as list-forms, get-form-schema and request-human-review-with-form to MCP clients for creating and querying review requests.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"gotohuman": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOTOHUMAN_API_KEY",
"mcp/gotohuman"
],
"env": {
"GOTOHUMAN_API_KEY": "<GOTOHUMAN_API_KEY>"
}
}
}
}
Run commanddocker run -i --rm -e GOTOHUMAN_API_KEY mcp/gotohuman
Environment variables to set
GOTOHUMAN_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocimcp/gotohuman

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
gotoHuman Logo

gotoHuman MCP Server

gotoHuman makes it easy to add human approvals to AI agents and agentic workflows.
A fully-managed async human-in-the-loop workflow with a customizable approval UI.
Enjoy built-in auth, webhooks, notifications, team features, and an evolving training dataset.

Use our MCP server to request human approvals from your AI workflows or use it to help with integration.

Usage

Available on npm as:

@gotohuman/mcp-server
Setup in Cursor / Claude / etc.
{
  "mcpServers": {
    "gotoHuman": {
      "command": "npx",
      "args": ["-y", "@gotohuman/mcp-server"],
      "env": {
        "GOTOHUMAN_API_KEY": "your-api-key"
      }
    }
  }
}

Install MCP Server

Get your API key and set up an approval step at app.gotohuman.com

Tools

list-forms

List all available review types.

  • Returns a list of all available review types in your account incl. high-level info about the added fields
get-form-schema

Get the schema to use when requesting a human review for a given review type.

  • Params
    • formId: The review type ID to fetch the schema for
  • Returns the schema, considering the incl. fields and their configuration
request-human-review-with-form

Request a human review. Will appear in your gotoHuman inbox.

  • Params
    • formId: The ID of the review type to use
    • fieldData: Content (AI-output to review, context,...) and configuration for the review type's fields.
      The schema for this needs to be fetched with get-form-schema
    • config: Configuration for the review type. Optional. The schema for this needs to be fetched with get-form-schema
    • title: Optional title shown in the inbox and notifications
    • webhookUrl: Optional webhook URL for this request (Static URLs can be set on the review type or the agent in gotoHuman)
    • workflow: Optional object linking this review to a multi-step agentic workflow:
      • runId: Unique ID for the current workflow run to link multiple steps.
    • metadata: Optional additional data that will be incl. in the webhook response after review template submission
    • assignToUsers: Optional list of user emails to assign the review to
  • Returns reviewId and reviewLink

Development

# Install dependencies
npm install

# Build the server
npm run build

# For testing: Run the MCP inspector
npm run inspector
Run locally in MCP Client (e.g. Cursor / Claude / Windsurf)
{
"mcpServers": {
  "gotoHuman": {
    "command": "node",
    "args": ["/<absolute-path>/build/index.js"],
    "env": {
      "GOTOHUMAN_API_KEY": "your-api-key",
      "GOTOHUMAN_AGENT_ID": "your-agent-id"
    }
  }
}
}

Note

For Windows, the args path needs to be C:\\<absolute-path>\\build\\index.js

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.