home / mcp / hiveflow mcp server

HiveFlow MCP Server

Bridges AI assistants with HiveFlow to manage and execute flows, retrieve data, and monitor MCP actions.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "hiveflowai-hiveflow-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@hiveflow/mcp-server"
      ],
      "env": {
        "HIVEFLOW_API_KEY": "your-api-key-here",
        "HIVEFLOW_API_URL": "https://api.hiveflow.ai",
        "HIVEFLOW_INSTANCE_ID": "instance_01"
      }
    }
  }
}

You can connect your AI assistants directly to HiveFlow through the HiveFlow MCP Server. It serves as a bridge that lets your copilots manage and trigger HiveFlow automation flows, access flow data, and execute MCP actions from your AI workspace.

How to use

Set up the MCP server as a local bridge and configure your MCP client to communicate with it. Once connected, you can issue MCP actions to manage flows, retrieve flow details, and monitor executions from your AI assistant. Your client will reference the configured MCP server to perform actions like creating flows, listing them, running executions, and inspecting history.

How to install

Prerequisites: Node.js and npm or npx installed on your machine. Ensure you have a modern Node.js runtime (recommended: LTS release). Then install the MCP server globally and prepare your environment.

# Install the MCP server globally
npm install -g @hiveflow/mcp-server

Configuration and usage notes

Configure your MCP client to point to the HiveFlow MCP server. Use the standard npx invocation to run the MCP server locally in your environment and supply your API credentials and HiveFlow URL.

{
  "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 access control

All API keys are transmitted over HTTPS and requests are authenticated. The MCP server does not store data locally, and access is controlled via the API key you provide during configuration.

Available tools

create_flow

Create a new automation flow in HiveFlow.

list_flows

List all your automation flows.

get_flow

Get details for 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

Retrieve the execution history for flows.

list_mcp_servers

List configured MCP servers.