gotohuman
MCP server from gotohuman/gotohuman-mcp-server
claude mcp add --transport stdio gotohuman-gotohuman-mcp-server npx -y @gotohuman/mcp-server \ --env GOTOHUMAN_API_KEY="your-api-key"
How to use
gotoHuman MCP server enables requesting human approvals from AI workflows via MCP and can be integrated into IDEs or agents. It ships with a built-in approval UI and supports authentication, webhooks, notifications, and team collaboration for managing approval tasks. The server exposes commands to interact with forms and approvals, such as listing available forms, retrieving form schemas, and requesting human reviews with contextual data. To use it, provide your gotoHuman API key as an environment variable (GOTOHUMAN_API_KEY) when running the MCP server. Once running, you can invoke tools like list-forms to fetch available review forms, get-form-schema with a formId to understand required fields, and request-human-review-with-form to submit AI-output or context for human review. You can also run the server locally via Node (npx @gotohuman/mcp-server) and pass your API key to enable authentication and routing to your gotoHuman workspace.
How to install
Prerequisites:
- Node.js and npm installed on your system
- Access to a gotoHuman account with an API key
Install and run the MCP server:
- Install and start via npx (recommended for quick setup):
npx -y @gotohuman/mcp-server
- Set your API key when running the server (example environment usage):
GOTOHUMAN_API_KEY=your-api-key npx -y @gotohuman/mcp-server
- If you prefer to embed the server in your own workflow, you can use the provided configuration block in your MCP client:
{
"mcpServers": {
"gotoHuman": {
"command": "npx",
"args": ["-y", "@gotohuman/mcp-server"],
"env": {
"GOTOHUMAN_API_KEY": "your-api-key"
}
}
}
}
- For local development and testing, you can also build and run the server with Node if you clone the repository and install dependencies, then run the built entry (example path may vary):
npm install
npm run build
node /<absolute-path>/build/index.js
Additional notes
Tips and considerations:
- Ensure GOTOHUMAN_API_KEY is kept secret and not checked into version control.
- If running locally, provide the absolute path to the built server when using the node-based invocation.
- The MCP client configuration can be embedded in your orchestration tooling to programmatically launch gotoHuman as part of your AI workflow pipeline.
- If you encounter issues with authentication, verify API key permissions in your gotoHuman account and ensure network access to the gotoHuman API is allowed.
- When running via npx, the server installs temporarily; for longer-running setups, consider a persistent installation or using the Node-based run approach with a built index.js.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.