What environment variables are required?
`NOTION_API_KEY` is required. Optional variables include `TRANSPORT` (stdio or sse), `HOST`, `PORT`, and `PYTHONPATH`.
@thestumonkey
基本信息
fastmcp implementation of notion-mcp server with support for extensible custom objects and functions
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"notion-chakra-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/path/to/notion-chakra-mcp/data:/app/data",
"-e",
"TRANSPORT",
"-e",
"NOTION_API_KEY",
"-e",
"HOST",
"-e",
"PORT",
"-e",
"PYTHONPATH=/app/src",
"notion-chakra-mcp"
],
"env": {
"TRANSPORT": "stdio",
"NOTION_API_KEY": "your_notion_api_key",
"HOST": "0.0.0.0",
"PORT": "8050"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Notion Chakra MCP is a Notion integration service that provides MCP (Message Control Protocol) endpoints for interacting with Notion databases and pages. It supports both stdio and SSE transports and is intended for developers using MCP clients like Cursor.
Configure Notion Chakra MCP as an MCP server in your client’s mcp.json (e.g., ~/.cursor/mcp.json), using a Docker container. Set the NOTION_API_KEY environment variable and optionally choose stdio or sse transport. Alternatively, use Docker Compose or direct Docker commands. A data directory must exist for persistence.
`NOTION_API_KEY` is required. Optional variables include `TRANSPORT` (stdio or sse), `HOST`, `PORT`, and `PYTHONPATH`.
Set the `TRANSPORT` environment variable to `stdio` or `sse`. The default is `stdio`.
A `data` directory must be mounted at `/app/data` inside the container. It stores schemas, database mappings, and other persistent data.
Install test dependencies with `pip install -r requirements.txt`, then run `python -m pytest tests/ -v`.
Project context your AI can query through MCP — with source evidence.

Model Context Protocol Servers

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
评论