What dependencies or runtime are required?
Python 3.x and the packages installed via pip. For MCP support, install with the `[mcp]` extra.
@phoenine
Basic information
A simple MCP server that integrates with Notion's API to manage my personal habit track.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"notion-mcp": {
"command": "uvx",
"args": [
"notion-mcp"
],
"env": {
"NOTION_TOKEN": "",
"ROOT_PAGE_ID": ""
}
}
}
}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.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Notion MCP Client is a Model Context Protocol (MCP) client for interacting with the Notion API, designed for use in AI tools like Claude that support MCP. It can also fall back to a standard HTTP API when MCP is not available.
Install via pip install notion-mcp (or with MCP support: pip install notion-mcp[mcp]). Configure a .env file with your Notion token and root page ID. Run the CLI with notion-mcp or start the server with notion-mcp-server --host 0.0.0.0 --port 8000. You can also supply a JSON configuration file.
fill_web_urlNotionRequestHandler classPython 3.x and the packages installed via pip. For MCP support, install with the `[mcp]` extra.
A Notion API token (`NOTION_TOKEN`) and a root page ID (`ROOT_PAGE_ID`) are required, set via environment variables or a JSON configuration file.
Data remains in Notion. The client reads and writes to your Notion workspace through the Notion API; no data is stored locally beyond configuration.
MCP (Model Context Protocol) when available; otherwise, the server falls back to a standard HTTP API that accepts POST requests at `/notion`.
The client uses configurable concurrency limits and retry delays (e.g., `CONCURRENCY_LIMIT=5`, `RETRY_DELAYS=1,3,5`) to respect Notion API rate limits. Only one operation (`fill_web_url`) is documented; more are planned.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

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,
Comments