Official Model Context Protocol (MCP) server for HiveFlow. Connect your AI assistants (Claude, Cursor, etc.) directly to your HiveFlow automation platform.
npm install -g @hiveflow/mcp-server
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"
}
}
}
}
{
"mcpServers": {
"hiveflow": {
"command": "npx",
"args": ["-y", "@hiveflow/mcp-server"],
"env": {
"HIVEFLOW_API_KEY": "your-api-key-here",
"HIVEFLOW_API_URL": "http://localhost:5000"
}
}
}
}
- Log in to your HiveFlow dashboard
- Go to Settings > API Keys
- Generate a new API key
cd your-hiveflow-backend
node get-api-key.js your-email@example.com
Once configured, you'll have access to these tools in your AI assistant:
-
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
-
list_mcp_servers
- List configured MCP servers -
create_mcp_server
- Register new MCP servers
-
hiveflow://flows
- Access to all your flows data -
hiveflow://mcp-servers
- MCP servers configuration -
hiveflow://executions
- Flow execution history
AI: "Create a flow called 'Email Processor' that analyzes incoming emails"
AI: "Show me all my active flows"
AI: "Execute the flow with ID 'abc123' with input data {email: 'test@example.com'}"
AI: "What's the status of my Email Processor flow?"
-
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)
hiveflow-mcp --api-key YOUR_KEY --api-url https://your-instance.com
This MCP server acts as a bridge between your AI assistant and HiveFlow:
AI Assistant (Claude/Cursor) ↔ MCP Server ↔ HiveFlow API
- API keys are transmitted securely over HTTPS
- All requests are authenticated and authorized
- No data is stored locally by the MCP server
"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
For detailed logging, set the environment variable:
export DEBUG=hiveflow-mcp:*
We welcome contributions! Please see our Contributing Guide for details.
MIT License - see LICENSE file for details.
Made with ❤️ by the HiveFlow team