ptt_mcp_server
The best PTT MCP server
claude mcp add --transport stdio pyptt-ptt_mcp_server docker run -i --rm -e PTT_ID -e PTT_PW ghcr.io/pyptt/ptt_mcp_server:latest \ --env PTT_ID="YOUR_PTT_ID" \ --env PTT_PW="YOUR_PTT_PW"
How to use
PTT MCP Server exposes a Docker-based instance that authenticates to PTT via PyPtt. To use it, configure your MCP client (for example Gemini CLI) to launch the Docker image when selecting the PTT MCP server. The client passes commands (such as login, fetch articles, post replies) to the server, which then uses PyPtt to interact with PTT on your behalf and returns results to the client. The provided example shows how to set up a container that receives environment variables for your PTT credentials and runs the server interactively.
Typical interactions include logging in to PTT, reading lists of articles, posting new content, replying to threads, and querying user or board information. The server acts as a bridge between your MCP client and PTT, enabling automated workflows and scripting for PTT tasks via the MCP protocol.
How to install
Prerequisites:
- Docker installed and running on the host where you will run the MCP client and/or server image.
- An MCP client that supports Docker-based MCP servers (e.g., Gemini CLI or similar).
Steps:
-
Install Docker (if not already installed).
- Follow the official guide for your OS: https://docs.docker.com/get-docker/
-
Pull and run the MCP server container manually (example):
# Replace YOUR_PTT_ID and YOUR_PTT_PW with your actual PTT credentials or rely on environment variables provided by your MCP client
export PTT_ID=YOUR_PTT_ID
export PTT_PW=YOUR_PTT_PW
docker run -it --rm \
-e PTT_ID \
-e PTT_PW \
ghcr.io/pyptt/ptt_mcp_server:latest
- Configure your MCP client to use this server via the mcpServers configuration (see mcp_config example in this document).
- Start the MCP client and test by issuing a simple command like login to PTT through the MCP bridge.
Note: If you prefer to automate with your client’s settings JSON, you can embed the docker-based configuration directly in your client’s mcpServers section as shown in the mcp_config field.
Additional notes
Tips and caveats:
- The Docker image ghcr.io/pyptt/ptt_mcp_server:latest expects PTT credentials to be supplied via environment variables PTT_ID and PTT_PW. Do not commit real credentials in shared config; use secure env management in your MCP client.
- The MCP client should keep the container run session interactive (-i) to receive commands in real-time.
- If you encounter network or authentication issues, verify that your PTT account credentials are correct and that Docker has network access to any required external services.
- This server relies on PyPtt under the hood; ensure PyPtt compatibility with your PTT account state (PTT may require additional verification under certain conditions).
- For production deployments, consider using a managed environment for secrets and rotating credentials as needed.
Related MCP Servers
unsplash
🔎 A MCP server for Unsplash image search.
pydantic-rpc
PydanticRPC is a Python library for rapidly exposing Pydantic models as gRPC, ConnectRPC, and MCP services without protobuf files.
python
🔐 Plug-and-play auth for Python MCP servers.
mcp-android -python
MCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.
Vector-Knowledge-Base
A semantic search engine that transforms your documents into an intelligent, searchable knowledge base using vector embeddings and AI
github-second-brain
Providing tools to AI to explore github codebase like agent