Cover image
Try Now
2025-03-23

镜像://github.com/port-experimenth/port-mcp-server

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

Port MCP Server

A Model Context Protocol (MCP) server for the Port.io API, enabling Claude to interact with Port.io's developer platform capabilities.

Installation

Obtain your Port credentials

  1. Create a Port.io Account:

    • Visit Port.io
    • Sign up for an account if you don't have one
  2. Create an API Key:

    • Navigate to your Port.io dashboard
    • Go to Settings > Credentials
    • Save both the Client ID and Client Secret

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "port": {
      "command": "uvx",
      "args": [
        "mcp-server-port@0.1.4",
        "--client-id", "YOUR_CLIENT_ID",
        "--client-secret", "YOUR_CLIENT_SECRET",
        "--region", "REGION" # US or EU
      ]
    }
  }
} 

Cursor

  1. Make sure uvx is installed:
pip install uvx
  1. Get its location:
which uvx
# Example output: /Users/janedoe/.local/bin/uvx
  1. Create a script to run the server:
# run-port-mcp.sh

cd /Users/janedoe/.local/bin/uvx

# Run the server with the specified credentials
./.venv/bin/uvx mcp-server-port@0.1.4 --client-id YOUR_CLIENT_ID --client-secret YOUR_CLIENT_SECRET --region YOUR_REGION
  1. Make it executable:
chmod +x /path/to/your/file/run-port-mcp.sh
  1. Configure in Cursor settings:
    • Go to Cursor settings > MCP Servers
    • Configure with:
      • Name - Port
      • Type - Command
      • Command - /path/to/your/file/run-port-mcp.sh

Cursor MCP Screenshot

Capabilities

Agent Tools

  1. trigger_port_agent
    • Trigger the Port.io AI agent with a prompt and wait for completion
    • Required inputs:
      • prompt (string): The prompt to send to the Port.io AI agent
    • Returns: Agent response with status, output, and any required actions
    • Note: The agent may return action URLs for bug reports or other tasks that require user interaction

Blueprint Tools

  1. get_blueprints

    • Retrieve a list of all blueprints from Port
    • Optional inputs:
      • detailed (boolean, default: false): Return complete schema details for each blueprint
    • Returns: Formatted text representation of all available blueprints
  2. get_blueprint

    • Retrieve information about a specific blueprint by its identifier
    • Required inputs:
      • blueprint_identifier (string): The unique identifier of the blueprint to retrieve
    • Optional inputs:
      • detailed (boolean, default: true): Return complete schema details
    • Returns: Formatted text representation of the specified blueprint

Entity Tools

Will be added in the future.

Development

Local Setup

  1. Create and activate a virtual environment:
# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows
  1. Install dependencies:
# Install in development mode
pip install -e .

# Install development dependencies
pip install -r requirements-dev.txt
  1. Run the server locally:
python -m src.mcp_server_port --client-id "CLIENT_ID" --client-secret "CLIENT_SECRET" --region "REGION"

Publishing a New Version

There are two ways to publish a new version: manually following all steps, or using the automated Make commands.

Manual Process

  1. Ensure you're on the main branch and it's up to date:
git checkout main
git pull origin main
  1. Merge the feature/release branch with changelog updates:
git merge feature/your-release-branch
  1. Update version in pyproject.toml

  2. Commit version bump:

git add pyproject.toml
git commit -m "chore: bump version to X.Y.Z"
git push origin main
  1. Create and push a new Git tag:
git tag -a vX.Y.Z -m "Release version X.Y.Z"
git push origin vX.Y.Z
  1. Build and publish to PyPI:
# Ensure you have the latest build tools
pip install --upgrade build twine

# Build the package
python -m build

# Check the package
twine check dist/*

# Upload to PyPI
twine upload dist/mcp_server_port-X.Y.Z*
  1. Create a GitHub release:
    • Go to the repository's Releases page
    • Click "Create new release"
    • Select the tag you just pushed
    • Title it "Release X.Y.Z"
    • Include the changelog in the description
    • Publish the release

Automated Process

You can use the provided Makefile commands to automate the release process:

# Update version and create release
make release VERSION=X.Y.Z

# Or run steps individually:
make bump-version VERSION=X.Y.Z  # Updates pyproject.toml
make tag VERSION=X.Y.Z          # Creates and pushes git tag
make build                      # Builds the package
make publish                    # Publishes to PyPI

Note: The automated process still requires you to manually create the GitHub release with changelog information.

Troubleshooting

If you encounter authentication errors, verify that:

  1. Your Port credentials are correctly set in the arguments
  2. You have the necessary permissions
  3. The credentials are properly copied to your configuration

License

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

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Bora Yalcin
  • Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • Lists Tailwind CSS classes in monospaced font

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • Yasir Eryilmaz
  • AI scriptwriting assistant for short, engaging video content.

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • jae-jae
  • MCP服务器使用剧作《无头浏览器》获取网页内容。

  • HiveNexus
  • 一个适用于中小型团队的AI聊天机器人,支持DeepSeek,Open AI,Claude和Gemini等车型。 专为中小团队设计的ai聊天应用,支持deepSeek,打开ai,claude,双子座等模型。

    Reviews

    5 (1)
    Avatar
    user_qlqim4v4
    2025-04-16

    I've been using MCP Server for Qdrant by Jimmy974 and it has been a game-changer for my data management needs. The integration with Qdrant is seamless, and the server's performance is impressive. It's user-friendly and efficient. Highly recommended for anyone looking to streamline their data processing workflows. Check it out at https://mcp.so/server/mcp-server-qdrant/Jimmy974.