gotoHuman MCP Server
by gotohuman
The gotoHuman MCP Server allows AI agents to request human reviews via MCP. It provides an async webhook-based workflow for autonomous agents and AI automations to review AI-generated content, approve critical actions, or provide input.
Last updated: N/A
What is gotoHuman MCP Server?
The gotoHuman MCP Server is a tool that enables AI agents to request and receive human feedback on their outputs or actions through the gotoHuman platform. It acts as a bridge between AI systems and human reviewers, facilitating a seamless review process.
How to use gotoHuman MCP Server?
- Get your API key and set up review forms at app.gotohuman.com.
- Install dependencies using
npm install. - Build the server using
npm run build. - Configure your MCP client (e.g., Cursor, Claude) to use the server, providing the path to the built index.js file and your API key in the environment variables.
Key features of gotoHuman MCP Server
Async webhook-based workflow
Integration with gotoHuman platform
Support for custom review forms
Ability to assign reviews to specific users
Tools to list forms and get form schemas
Use cases of gotoHuman MCP Server
Reviewing AI-generated content
Approving critical actions by AI agents
Providing human input to AI workflows
Validating AI outputs for accuracy and quality
Gathering feedback on AI-driven decisions
FAQ from gotoHuman MCP Server
How do I get an API key?
How do I get an API key?
You can obtain an API key by signing up and setting up your review forms at app.gotohuman.com.
What is a review form?
What is a review form?
A review form defines the structure and fields for human reviewers to provide feedback on AI-generated content or actions.
How do I configure my MCP client to use this server?
How do I configure my MCP client to use this server?
You need to add a configuration block to your MCP client settings, specifying the command to run the server, the path to the built index.js file, and your API key as an environment variable. Refer to the example provided in the README.
What kind of data can I send for review?
What kind of data can I send for review?
You can send any type of data that can be represented in a form, including text, code snippets, images, and more. The specific fields and data types will depend on the schema of the review form you are using.
How do I handle the webhook response after a review is submitted?
How do I handle the webhook response after a review is submitted?
The webhook response will contain the data provided by the human reviewer, along with any metadata you included in the original request. You can use this data to update your AI system, trigger further actions, or log the review outcome.