What are the prerequisites to use this integration?
You need access to the Planning Center API, a Python environment, an MCP client (such as Claude Desktop), and API keys for authentication.
@jake-ccnh
Basic information
Planning Center Online MCP Server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"pco-mcp": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This integration connects the Planning Center Online (PCO) API with an MCP server, enabling a Large Language Model (LLM) to answer natural language queries and retrieve data from Planning Center. It is designed for users who want to interact with their Planning Center data conversationally.
Clone the repository, install dependencies with uv pip install -r requirements.txt, and configure PCO_SECRET_KEY and PCO_APPLICATION_ID as environment variables. Test the server using fastmcp dev services.py, then add the provided MCP server configuration to your MCP client (e.g., Claude Desktop). Send natural language queries to the server, which processes them and interacts with the PCO API to return structured responses or perform actions.
You need access to the Planning Center API, a Python environment, an MCP client (such as Claude Desktop), and API keys for authentication.
Set the environment variables `PCO_SECRET_KEY` for your Planning Center API key and `PCO_APPLICATION_ID` for the URL of the MCP server.
The README does not specify the underlying transport; it references FASTMCP and demonstrates usage via an MCP client configuration using the `fastmcp run` command.
The project states that future work intends to continue development on other areas of Planning Center, implying current scope may be limited to services.
You need Python, the packages listed in `requirements.txt` (installed via `uv pip install`), and access to the Planning Center Online API.
Search, understand, reproduce, and improve an idea with ease
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.
ArduPilotドローンをAIエージェントから操作するMCPサーバーです。
Comments