Conductor MCP

What is Conductor MCP about?

Provides an MCP server that allows AI assistants (e.g., Claude, Cursor) to interact with an Orkes Conductor instance, performing workflow creation, execution, and monitoring directly from conversational prompts.

How to use Conductor MCP?

1. Install the package with pip install conductor-mcp.
2. Create a JSON config containing CONDUCTOR_SERVER_URL, CONDUCTOR_AUTH_KEY, and CONDUCTOR_AUTH_SECRET.
3. Run the server:

   conductor-mcp --config /absolute/path/to/config.json
   

   Alternatively, use uv run conductor-mcp --config … for isolated environments.
4. Add the server to your AI assistant by referencing the MCP configuration (see Claude and Cursor examples in the README).

Key Features

• Simple CLI (conductor-mcp) with --config flag.
• Supports configuration via JSON file or environment variables.
• Works with any Model Context Protocol‑compatible AI agent.
• No additional infrastructure required; runs as a stand‑alone process.
• Includes a local_development.py helper for quick local testing.

Use Cases

• Automating data‑gathering workflows (e.g., weather‑risk analysis for aviation).
• Scheduled stock‑monitoring and notification pipelines.
• Orchestrating multi‑step API calls from natural‑language prompts.
• Rapid prototyping of AI‑driven automation without writing boilerplate code.

FAQ

Q: Do I need a Conductor server to run this? A: Yes, an accessible Conductor instance is required; provide its URL and authentication keys in the config.

Q: Can I run the server without a config file? A: Yes, set the three required environment variables (CONDUCTOR_SERVER_URL, CONDUCTOR_AUTH_KEY, CONDUCTOR_AUTH_SECRET).

Q: Is this compatible with other AI agents besides Claude and Cursor? A: Any agent that supports the Model Context Protocol can connect using the same mcpServers configuration.

Q: How do I develop locally? A: Use the --local_dev flag, which loads local_development.py to set environment variables automatically.

oss-conductor-mcp

Model Context Protocol server for Conductor.

This package is used to run an MCP server that is capable of interacting with a Conductor instance. It provides tools for the basic operations that may be needed by an MCP client for Workflow creation, execution, and analysis.

PyPi Quickstart

Install package

pip install conductor-mcp

Create a JSON config with your Conductor keys

{
  "CONDUCTOR_SERVER_URL": "https://developer.orkescloud.com/api",
  "CONDUCTOR_AUTH_KEY": "<YOUR_APPLICATION_AUTH_KEY>",
  "CONDUCTOR_AUTH_SECRET": "<YOUR_APPLICATION_SECRET_KEY>"
}

Note: the /api path is required as part of the CONDUCTOR_SERVER_URL for most applications

Plug the server into an AI Agent, such as Claude or Cursor

{
  "mcpServers": {
    "conductor": {
      "command": "conductor-mcp",
      "args": [
        "--config",
        "<ABSOLUTE PATH TO A JSON CONFIG FILE>"
      ]
    }
  }
}

You should now be able to interact with Conductor via your AI Agent.

Adding to Claude

You can find instructions for adding to Claude here. In general, you just add the mcpServers config (above) to your Claude config (or create it if it doesn't exist). For instance, on Mac it might be ~/Library/Application\ Support/Claude/claude_desktop_config.json.

Adding to Cursor

The main Cursor instructions are here. Go to Cursor -> Settings -> Cursor Settings -> MCP and select "+ Add new global MCP server".

Here you can add the exact same configuration file shown in the example for Claude (above). You can then access the AI chat feature and explore the MCP server in the sidebar with ⌘+L (Mac) or Ctrl+L (Windows/Linux).

Example prompts

Get Flight Risk Info

Create and execute a Conductor Workflow that calls any necessary http endpoints to gather current weather data around
Seattle and outputs the risk factors for flying a small airplane around the South Lake Union area using Visual Flight
Rules today. Only use publicly available endpoints that don't require an API key.

Notify Stocks

(May require API Keys)

Create a Conductor Workflow that runs on a daily schedule, accepts a list of email address and a stock symbol, checks
current stock prices, and sends an email to everyone on the list if they should be happy or sad today based on stock
performance. Name the workflow "NotifyStonks" and use schemaVersion 2.

GitHub Quickstart

Clone GitHub Repo

gh repo clone conductor-oss/conductor-mcp

This project relies on uv https://docs.astral.sh/uv/getting-started/

Create venv

(not entirely necessary, since uv automatically creates and uses the virtual environment on its own when running other commands)

uv sync
source .venv/bin/activate

Define Env Vars

You can continue to use a JSON config file and the --config flag, or if the server is running in an environment where you have control over the environment variables the MCP server will look for them there if a config file is not provided.

export CONDUCTOR_SERVER_URL="YOUR_CONDUCTOR_SERVER_URL"
export CONDUCTOR_AUTH_KEY="<YOUR_APPLICATION_AUTH_KEY>"
export CONDUCTOR_AUTH_SECRET="<YOUR_APPLICATION_SECRET_KEY>"

Configure Your AI Assistant

{
  "mcpServers": {
    "conductor": {
      "command": "uv",
      "args": [
        "--directory",
        "<ABSOLUTE_PATH_TO_THE_PROJECT>",
        "run",
        "conductor-mcp",
        "--config",
        "<ABSOLUTE PATH TO A JSON CONFIG FILE>"
      ]
    }
  }
}

Or Run Server Directly

cd <PROJECT_ROOT>
uv run conductor-mcp --config <ABSOLUTE PATH TO A JSON CONFIG FILE>

Note: a local_development.py also exists for setting env vars and will be used when the --local_dev flag is set.