Skip to main content
Glama
saymine

Conductor MCP Server

by saymine

Conductor mcp server

用于 Conductor 的 Model Context Protocol 服务器。

此包用于运行一个能够与 Conductor 实例交互的 MCP 服务器。它为 MCP 客户端提供了工作流创建、执行和分析所需的基本操作工具。

PyPi 快速入门

安装包

pip install conductor-mcp

使用您的 Conductor 密钥创建 JSON 配置

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

注意:对于大多数应用程序,/api 路径是 CONDUCTOR\_SERVER\_URL 的必需部分

将服务器接入 AI 代理(如 Claude 或 Cursor)

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

您现在应该可以通过 AI 代理与 Conductor 进行交互了。

添加到 Claude

您可以在此处找到添加到 Claude 的说明 此处。 一般来说,您只需将 mcpServers 配置(上文)添加到您的 Claude 配置中(如果不存在则创建)。例如, 在 Mac 上,它可能是 ~/Library/Application\ Support/Claude/claude_desktop_config.json

添加到 Cursor

主要的 Cursor 说明在 此处。 前往 Cursor -> Settings -> Cursor Settings -> MCP,然后选择 "+ Add new global MCP server"。

在这里,您可以添加与上述 Claude 示例中完全相同(如上所示)的配置文件。 然后,您可以访问 AI 聊天功能,并在 侧边栏中使用 ⌘+L(Mac)或 Ctrl+L(Windows/Linux) 探索 MCP 服务器。

示例提示词

获取航班风险信息

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.

通知股票

(可能需要 API 密钥)

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 快速入门

克隆 GitHub 仓库

gh repo clone conductor-oss/conductor-mcp

此项目依赖于 uv https://docs.astral.sh/uv/getting-started/

创建虚拟环境

(并非完全必要,因为 uv 在运行其他命令时会自动创建并使用虚拟环境)

uv sync
source .venv/bin/activate

定义环境变量

您可以继续使用 JSON 配置文件及 --config 标志,或者如果服务器运行在您能控制环境变量的环境中, MCP 服务器将在未提供配置文件时从这些环境变量中读取。

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

配置您的 AI 助手

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

或直接运行服务器

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

注意:还存在一个 local_development.py 用于设置环境变量,当设置 --local_dev 标志时将会使用它。

-
license - not tested
Not graded
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

  • MCP server for AI access to Swagger by SmartBear.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/saymine/conductor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server