gotoHuman MCP Server

What does “gotoHuman” MCP Server do?

The gotoHuman MCP Server is a tool designed to seamlessly integrate human-in-the-loop workflows into AI assistants and agentic development environments. It enables AI agents to request human approvals via customizable review forms, track approval steps, and manage notifications and team-based workflows. With built-in authentication, webhook support, and a robust UI for approvals, gotoHuman enhances development workflows that require oversight, compliance, or manual validation. By exposing its capabilities through the Model Context Protocol (MCP), it empowers AI-driven processes to interact directly with external human stakeholders, making tasks like content moderation, code review, or approval-based automation more efficient and auditable.

List of Prompts

No specific prompt templates are mentioned in the available content.

List of Resources

No specific MCP resources are listed in the available content.

List of Tools

• list-forms
  Lists all available review forms in your account, including high-level information about the fields added to each form.

• get-form-schema
  Retrieves the schema for a specific review form, including fields and their configuration, which is required when requesting a human review.

• request-human-review-with-form
  Initiates a human review using a chosen form, providing content, configuration, and metadata. Assigns the review to specific users if needed and returns a link to the review in gotoHuman.

Use Cases of this MCP Server

• Human-in-the-loop Approvals
  Integrate approval steps into automated workflows, ensuring that critical decisions—such as content publication, code deployment, or sensitive data handling—are validated by a human before proceeding.

• Custom Review Forms for Moderation
  Use customizable forms to collect human feedback or moderation decisions on AI-generated outputs, helping teams enforce quality standards and compliance requirements.

• Workflow Automation with Human Oversight
  Automate repetitive processes while retaining the ability for human intervention at key stages, such as user onboarding or transaction reviews.

• Collaborative Team Approvals
  Assign reviews to specific team members, track approval status, and manage notifications, streamlining team-based decision-making.

• Integration with IDEs and Agentic Tools
  Enable AI assistants in developer environments (such as Cursor, Claude, or Windsurf) to request human input during code reviews or architectural decisions, reducing bottlenecks and improving workflow transparency.

How to set it up

Windsurf

1. Ensure you have Node.js installed.
2. Obtain your GOTOHUMAN_API_KEY from app.gotohuman.com.
3. Edit your Windsurf configuration file to add the MCP server:

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

4. Save your configuration and restart Windsurf.
5. Verify the server is running by initiating a test approval.

Claude

1. Install Node.js if not already installed.
2. Get your API key from app.gotohuman.com.
3. Update your Claude configuration file as follows:

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

4. Save your configuration and restart Claude.
5. Confirm integration by requesting a human review.

Cursor

1. Make sure Node.js is installed.
2. Retrieve your API key from app.gotohuman.com.
3. Insert this into your Cursor configuration:

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

4. Save and restart Cursor.
5. Test by triggering a sample approval flow.

Cline

1. Set up Node.js if you haven’t already.
2. Get your GOTOHUMAN_API_KEY from app.gotohuman.com.
3. Add the MCP server to your Cline configuration:

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

4. Save your changes and restart Cline.
5. Check functionality by requesting a human review.

Securing API keys:
Use environment variables in your configuration for sensitive keys:

{
  "mcpServers": {
    "gotoHuman": {
      "command": "npx",
      "args": ["-y", "@gotohuman/mcp-server"],
      "env": {
        "GOTOHUMAN_API_KEY": "${GOTOHUMAN_API_KEY}"
      }
    }
  }
}

Set the actual environment variable in your system or deployment environment.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gotoHuman": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “gotoHuman” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Roots Support | ⛔ (Not mentioned) | | Sampling | ⛔ (Not mentioned) |

Based on the provided documentation, the gotoHuman MCP Server is focused, easy to set up, and exposes clear tools, but lacks documentation on prompt templates, explicit MCP resources, and sampling/roots features. This makes it solid for its core use case but less full-featured than some alternatives for broader MCP integration.

Our opinion

The gotoHuman MCP Server is well-documented for installation, tool usage, and API key management, and it delivers on its primary human-in-the-loop promise. However, it lacks detailed documentation on MCP prompt templates, resources, and advanced MCP features like roots and sampling. This would make it a reliable, purpose-driven server for approval workflows, but less versatile for those seeking broader MCP extensibility.

MCP Score