gotoHuman

gotoHuman MCP Server

Let your AI agents ask for human reviews in gotoHuman via MCP.
Review AI-generated content, approve critical actions or provide input.
An async webhook-based workflow for autonomous agents and AI automations.

Demo

This is Cursor on the left, but this could be a background agent that also reacts to the approval webhook to add an item to your list of newsletter ideas.

https://github.com/user-attachments/assets/380a4223-ea77-4e24-90a5-52669b77f56f

Setup

Get your API key and set up your review forms at app.gotohuman.com

1# Install dependencies
2npm install
3
4# Build the server
5npm run build
6
7# For testing: Run the MCP inspector
8npm run inspector

Tools

`list-forms`

List all available review forms.

Returns a list of all available forms 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 form.

Params
- formId: The form 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 form ID for the review
- fieldData: Content (AI-output to review, context,...) and configuration for the form's fields.
  The schema for this needs to be fetched with get-form-schema
- metadata: Optional additional data that will be incl. in the webhook response after form submission
- assignToUsers: Optional list of user emails to assign the review to
Returns a link to the review in gotoHuman

Use in MCP client

Cursor or Claude

1{
2"mcpServers": {
3  "gotoHuman": {
4    "command": "node",
5    "args": ["/<absolute-path>/build/index.js"],
6    "env": {
7      "GOTOHUMAN_API_KEY": "your-api-key"
8    }
9  }
10}
11}

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

Contents