mcpField
M
mcp-server-flyder

mcp-server-flyder

Local
github.com/Streamline-TSAI & Agents0Updated 81w ago
Repository

About mcp-server-flyder

An MCP server for integrating Flyder workflows. It is in early development and provides tools to list a user's workflows and run one by ID with optional input.

Key features

  1. 01List workflows and their IDs
  2. 02Run a workflow by ID
  3. 03Pass optional input to a workflow

Use cases

  1. 01Find a workflow ID before running it
  2. 02Run a workflow with supplied text
  3. 03Run a workflow using its default input

MCP support

Exposes Flyder workflow listing and execution tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "flyder": {
      "command": "uvx",
      "args": [
        "mcp-server-flyder"
      ],
      "env": {
        "FLYDER_EMAIL": "<FLYDER_EMAIL>",
        "FLYDER_API_KEY": "<FLYDER_API_KEY>"
      }
    }
  }
}
Run commanduvx mcp-server-flyder
Environment variables to set
FLYDER_EMAIL
FLYDER_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-server-flyder

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server-flyder

MCP Server for Flyder

Overview

A Model Context Protocol server for Flyder workflow integration.

Please note that mcp-server-flyder is currently in early development. The functionality and available tools are subject to change as we continue to develop and improve the server.

Tools

  1. list_workflows

    • Get a list of workflows that belong to the user. This returns a dictionary that has workflow names and their IDs.
    • Input:
      • none
    • Returns: A list containing workflow names and their IDs. The IDs can later be used to run a specific workflow.

  2. run_workflow_by_id

    • Run a specific workflow using its ID.
    • Input:
      • workflow_id (int): The ID of the workflow to run.
      • input (str, optional): The input text to be passed to the workflow. If not provided, the default input from the workflow will be used.
    • Returns: An object containing the result of the workflow run.

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "flyder": {
      "command": "uvx",
      "args": [ 
        "mcp-server-flyder"
      ],
      "env": {
        "FLYDER_EMAIL": "<email used to sign up on Flyder>",
        "FLYDER_API_KEY": "<your Flyder API key>"
      }
    }
  }
}

Debugging

You can use the MCP inspector to debug the server.

cd path/to/repo
npx @modelcontextprotocol/inspector uv run mcp-server-flyder

Development

If you are doing local development, there are two ways to test your changes:

  1. Run the MCP inspector to test your changes. See Debugging for run instructions.

  2. Test using the Claude desktop app. Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "flyder": {
      "command": "uv",
      "args": [ 
        "--directory",
        "/<path to repo>",
        "run",
        "mcp-server-flyder"
      ],
      "env": {
        "FLYDER_EMAIL": "<email used to sign up on Flyder>",
        "FLYDER_API_KEY": "<your Flyder API key>"
      }
    }
  }
}

License

This MCP server is licensed under the GNU General Public License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the GNU License. For more details, please see the LICENSE file in the project repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.