home / mcp / hiveflow mcp server

HiveFlow MCP Server

Bridges AI assistants to HiveFlow, enabling flow management, execution, and MCP server configuration.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "punkpeye-hiveflow-mcp-server": {
      "url": "https://api.hiveflow.ai",
      "headers": {
        "HIVEFLOW_API_KEY": "your-api-key-here",
        "HIVEFLOW_API_URL": "https://api.hiveflow.ai",
        "HIVEFLOW_INSTANCE_ID": "instance-123"
      }
    }
  }
}

You set up and run the HiveFlow MCP Server to bridge your AI assistants with HiveFlow automation. This server lets you connect clients like Claude or Cursor to HiveFlow, enabling you to manage flows, execute automations, and configure MCP endpoints from a single, centralized server.

How to use

You interact with the MCP server through your MCP client configuration. Start the server locally or point your client to the remote HiveFlow MCP endpoint. When your client is configured, you can manage flows, execute automations, and administer MCP servers using the available MCP tools. All communications are authenticated and carried over HTTPS when using remote endpoints.

How to install

Prerequisites: ensure you have Node.js installed on your system. You also need npm to install or enable the MCP server runner.

Install the MCP server globally so you can run it from any project directory.

npm install -g @hiveflow/mcp-server

Additional configuration and usage notes

Configure your MCP client to connect to either a remote HiveFlow API or run the MCP server locally. Use the following example configurations as guidance.

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

Security and data handling

API keys are transmitted securely over HTTPS. All requests are authenticated and authorized. The MCP server does not store data locally.

Troubleshooting

If you encounter issues, verify your API key and API URL, ensure the HiveFlow API is reachable, and check firewall settings. If the MCP server cannot be found, restart your AI assistant, verify the MCP configuration file location, and confirm the MCP package is installed.

For detailed logs during development, enable debug logging by setting the DEBUG environment variable to hiveflow-mcp:*.

Available tools

Flow management: create_flow

Create new automation flows to define how data and actions move through your system.

Flow management: list_flows

List all configured automation flows in your HiveFlow instance.

Flow management: get_flow

Retrieve detailed information about a specific flow.

Flow management: execute_flow

Run a flow with provided inputs or triggers.

Flow management: pause_flow

Pause an active flow.

Flow management: resume_flow

Resume a paused flow.

Flow management: get_flow_executions

Inspect the execution history of flows.

MCP Server Management: list_mcp_servers

List configured MCP servers in your environment.