← Back to directory
G

gotoHuman MCP Server

Official
Add human approvals to AI agents and agentic workflows
GitHub source repository ↗
★ 52 Stars Category · Collaboration Popular Source revision a029557d54cd
50FMRS · D
Reliability
9/20
Security and permissions
10/20
Maintenance
11/20
Documentation
10/20
Setup experience
10/20

The gotoHuman MCP server provides a secure, controlled way to incorporate human approvals into AI workflows, simplifying the oversight of AI agents.

Read the FMRS scoring method →

The gotoHuman MCP server enables AI agents and agentic workflows to request human approvals via MCP. It provides a fully managed, async human-in-the-loop workflow with a customizable approval UI, built-in auth, webhooks, notifications, and team features. This server acts as a bridge between AI systems and human reviewers, enabling human oversight of AI outputs.

Tools

list-forms
List all available review templates in your account, including high-level info about added fields.
get-form-schema
Get the schema to use when requesting a human review for a given review template.
request-human-review-with-form
Request a human review. Will appear in your gotoHuman inbox.

Setup

Install using npx: npx @gotohuman/mcp-server. Configure your MCP client (e.g., Cursor, Claude, Windsurf) by adding an environment variable GOTOHUMAN_API_KEY with your API key. For local development, install dependencies with npm install, build with npm run build, and run as a local server using node /path/to/build/index.js.

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

Fit and risk

Best for

  • Developers building AI agents that require human supervision
  • Teams wanting to implement approval processes in AI workflows
  • Scenarios needing a customizable approval UI

Not for

  • Fully automated processes without human intervention
  • Offline or intranet environments (requires network connectivity)
  • On-premise deployments without the hosted service

Required permissions

  • Requires a GOTOHUMAN_API_KEY for authentication and access to forms in your account
  • Requires network access to app.gotohuman.com
  • Write operations involve the gotoHuman service, no direct local file access

Risks and side effects

  • Exposure of API key could lead to unauthorized approval requests
  • Network issues may disrupt communication with the service
  • Over-reliance on the service could cause delays in approvals

Troubleshooting

  1. Ensure your API key is correct and active.
  2. Check network connectivity to app.gotohuman.com.
  3. If using a local build, confirm the build succeeded and the path is correct.
  4. If tools fail, verify form IDs exist and fetch the correct schema using get-form-schema.

Use cases

Request human approval before AI agents execute critical actions
Review AI-generated outputs in automated workflows
Implement staged human approvals in multi-step agentic workflows
Integrate human oversight into AI-powered coding assistants

Supported clients

Claude DesktopFull support
CursorFull support
WindsurfFull support