Hiveflow MCP Server

What is Hiveflow MCP Server about?

Hiveflow MCP Server acts as a lightweight bridge between AI assistants (e.g., Claude, Cursor) and the HiveFlow automation platform. It implements the Model Context Protocol, exposing flow‑management operations as AI‑accessible tools so assistants can create, list, execute, and control workflow instances without writing custom integration code.

How to use Hiveflow MCP Server?

1. Install globally

npm install -g @hiveflow/mcp-server

2. Add a server entry to your AI‑assistant MCP configuration (e.g., .cursor/mcp.json):

{
  "mcpServers": {
    "hiveflow": {
      "command": "npx",
      "args": ["-y", "@hiveflow/mcp-server"],
      "env": {
        "HIVEFLOW_API_KEY": "<YOUR_API_KEY>",
        "HIVEFLOW_API_URL": "https://api.hiveflow.ai"
      }
    }
  }
}

Replace <YOUR_API_KEY> with a valid key from the HiveFlow dashboard. 3. Run your AI assistant. The assistant can now invoke tools such as create_flow, execute_flow, list_flows, etc., which are routed through the MCP server to the HiveFlow API.

Key features of Hiveflow MCP Server

• One‑command launch using npx for instant execution.
• Environment‑driven configuration (API key, API URL, optional instance ID).
• Full flow lifecycle support: create, list, retrieve, execute, pause, resume, and query execution history.
• MCP server management tools to list and register additional MCP servers.
• Secure communication: all requests are HTTPS‑encrypted and authenticated.
• Zero local data storage – the server solely forwards requests.

Use cases of Hiveflow MCP Server

• AI‑driven automation: let a conversational assistant build or modify workflows on‑the‑fly.
• Rapid prototyping: developers can test flow logic directly from the AI without manual API calls.
• Self‑hosted environments: point HIVEFLOW_API_URL to a local instance for testing or private deployments.
• Multi‑tenant orchestration: use HIVEFLOW_INSTANCE_ID to target specific tenant contexts.

FAQ from the Hiveflow MCP Server

Q: What happens if HIVEFLOW_API_KEY is missing? A: The server will abort startup with the error "HIVEFLOW_API_KEY is required". Set the variable in the MCP configuration.

Q: Can I run the server against a local HiveFlow instance? A: Yes. Set HIVEFLOW_API_URL to your local address (e.g., http://localhost:5000).

Q: How do I enable detailed logs? A: Set DEBUG=hiveflow-mcp:* in the environment before launching the server.

Q: Is any data persisted locally? A: No. The server forwards requests to the HiveFlow API and does not store data on disk.

Q: How do I add multiple MCP servers? A: Use the list_mcp_servers and create_mcp_server tools provided by the server to manage additional entries.

@hiveflow/mcp-server

Official Model Context Protocol (MCP) server for HiveFlow. Connect your AI assistants (Claude, Cursor, etc.) directly to your HiveFlow automation platform.

🚀 Quick Start

Installation

npm install -g @hiveflow/mcp-server

Configuration

Add to your MCP client configuration (e.g., .cursor/mcp.json):

{
  "mcpServers": {
    "hiveflow": {
      "command": "npx",
      "args": ["-y", "@hiveflow/mcp-server"],
      "env": {
        "HIVEFLOW_API_KEY": "your-api-key-here",
        "HIVEFLOW_API_URL": "https://api.hiveflow.ai"
      }
    }
  }
}

For Local Development

{
  "mcpServers": {
    "hiveflow": {
      "command": "npx",
      "args": ["-y", "@hiveflow/mcp-server"],
      "env": {
        "HIVEFLOW_API_KEY": "your-api-key-here",
        "HIVEFLOW_API_URL": "http://localhost:5000"
      }
    }
  }
}

🔑 Getting Your API Key

Option 1: From HiveFlow Dashboard

1. Log in to your HiveFlow dashboard
2. Go to Settings > API Keys
3. Generate a new API key

Option 2: From Command Line (Self-hosted)

cd your-hiveflow-backend
node get-api-key.js your-email@example.com

🛠️ Available Tools

Once configured, you'll have access to these tools in your AI assistant:

Flow Management

• create_flow - Create new automation flows
• list_flows - List all your flows
• get_flow - Get details of a specific flow
• execute_flow - Execute a flow with optional inputs
• pause_flow - Pause an active flow
• resume_flow - Resume a paused flow
• get_flow_executions - Get execution history

MCP Server Management

• list_mcp_servers - List configured MCP servers
• create_mcp_server - Register new MCP servers

📊 Available Resources

• hiveflow://flows - Access to all your flows data
• hiveflow://mcp-servers - MCP servers configuration
• hiveflow://executions - Flow execution history

💡 Usage Examples

Create a New Flow

AI: "Create a flow called 'Email Processor' that analyzes incoming emails"

List Active Flows

AI: "Show me all my active flows"

Execute a Flow

AI: "Execute the flow with ID 'abc123' with input data {email: 'test@example.com'}"

Get Flow Status

AI: "What's the status of my Email Processor flow?"

🔧 Configuration Options

Environment Variables

• HIVEFLOW_API_KEY - Your HiveFlow API key (required)
• HIVEFLOW_API_URL - Your HiveFlow instance URL (default: https://api.hiveflow.ai)
• HIVEFLOW_INSTANCE_ID - Instance ID for multi-tenant setups (optional)

Command Line Options

hiveflow-mcp --api-key YOUR_KEY --api-url https://your-instance.com

🏗️ Architecture

This MCP server acts as a bridge between your AI assistant and HiveFlow:

AI Assistant (Claude/Cursor) ↔ MCP Server ↔ HiveFlow API

🔒 Security

• API keys are transmitted securely over HTTPS
• All requests are authenticated and authorized
• No data is stored locally by the MCP server

🐛 Troubleshooting

Common Issues

"HIVEFLOW_API_KEY is required"

• Make sure you've set the API key in your MCP configuration
• Verify the API key is valid and not expired

"Cannot connect to HiveFlow API"

• Check that your HiveFlow instance is running
• Verify the API URL is correct
• Ensure there are no firewall restrictions

"MCP server not found"

• Restart your AI assistant completely
• Verify the MCP configuration file is in the correct location
• Check that the package is installed: npm list -g @hiveflow/mcp-server

Debug Mode

For detailed logging, set the environment variable:

export DEBUG=hiveflow-mcp:*

📚 Documentation

• HiveFlow Documentation
• MCP Protocol Specification
• API Reference

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

📄 License

MIT License - see LICENSE file for details.

🆘 Support

• GitHub Issues
• Discord Community
• Email Support

---

Made with ❤️ by the HiveFlow team