# Hubflo MCP Server

The official MCP Server for the [Hubflo API](https://www.hubflo.com), published on npm as [`hubflo-mcp-mcp`](https://www.npmjs.com/package/hubflo-mcp-mcp).

## Installation

No installation required. Use `npx` to run the server directly:

```sh
npx -y hubflo-mcp-mcp
```

### Running

```sh
export HUBFLO_MCP_API_KEY="My API Key"
npx -y hubflo-mcp-mcp
```

### Via MCP Client

There is a partial list of existing clients at [modelcontextprotocol.io](https://modelcontextprotocol.io/clients). If you already
have a client, consult their documentation to install the MCP server.

#### Claude Desktop

Add the following to your `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "hubflo": {
      "command": "npx",
      "args": ["-y", "hubflo-mcp-mcp"],
      "env": {
        "HUBFLO_MCP_API_KEY": "My API Key"
      }
    }
  }
}
```

#### Cursor

Add the following to your `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "hubflo": {
      "command": "npx",
      "args": ["-y", "hubflo-mcp-mcp"],
      "env": {
        "HUBFLO_MCP_API_KEY": "My API Key"
      }
    }
  }
}
```

## Code Mode

This MCP server is built on the "Code Mode" tool scheme. In this MCP Server,
your agent will write code against the TypeScript SDK, which will then be executed in an
isolated sandbox. To accomplish this, the server will expose two tools to your agent:

- The first tool is a docs search tool, which can be used to generically query for
  documentation about your API/SDK.

- The second tool is a code tool, where the agent can write code against the TypeScript SDK.
  The code will be executed in a sandbox environment without web or filesystem access. Then,
  anything the code returns or prints will be returned to the agent as the result of the
  tool call.

Using this scheme, agents are capable of performing very complex tasks deterministically
and repeatably.

## Running remotely

Launching the client with `--transport=http` launches the server as a remote server using Streamable HTTP transport. The `--port` setting can choose the port it will run on, and the `--socket` setting allows it to run on a Unix socket.

Authorization can be provided via the `Authorization` header using the Bearer scheme.

Additionally, authorization can be provided via the following headers:
| Header | Equivalent client option | Security scheme |
| ---------------------- | ------------------------ | --------------- |
| `x-hubflo-mcp-api-key` | `apiKey` | bearer_auth |

A configuration JSON for this server might look like this, assuming the server is hosted at `http://localhost:3000`:

```json
{
  "mcpServers": {
    "hubflo_mcp_api": {
      "url": "http://localhost:3000",
      "headers": {
        "Authorization": "Bearer <auth value>"
      }
    }
  }
}
```