What is the main modification of this fork?
The primary modification is the replacement of the transport mechanism from Stdio to Server-Sent Events (SSE).
@ContexaAI
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"notionApi": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"OPENAPI_MCP_HEADERS",
"mcp/notion"
],
"env": {
"OPENAPI_MCP_HEADERS": "{\"Authorization\":\"Bearer ntn_****\",\"Notion-Version\":\"2022-06-28\"}"
}
}
}
}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 project implements an MCP server for the Notion API. It is a fork of the official Notion MCP server that replaces the Stdio transport with Server-Sent Events (SSE). It allows AI assistants to interact with Notion pages, databases, and comments using natural language commands.
Install and configure the server by setting up an internal Notion Integration, copying the integration token, and adding the MCP configuration to your client (e.g., .cursor/mcp.json or claude_desktop_config.json). You can run it via npx or Docker, providing the token and Notion version in the OPENAPI_MCP_HEADERS environment variable. Then instruct your AI to perform actions like commenting or creating pages.
The primary modification is the replacement of the transport mechanism from Stdio to Server-Sent Events (SSE).
Go to https://www.notion.so/profile/integrations, create a new internal integration, and copy the token from the Configuration tab.
No. The scope of the Notion API exposed is limited; for example, you will not be able to delete databases via MCP. There is a non-zero risk to workspace data, so consider creating a read-only integration token.
Add the appropriate block to your client’s config file (e.g., `.cursor/mcp.json` or `claude_desktop_config.json`) using either `npx` or Docker, with your integration token and Notion version in the `OPENAPI_MCP_HEADERS` variable.
It requires Node.js (for `npx`) or Docker. The Docker image can be pulled from Docker Hub or built locally using the provided `docker-compose` file.

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
Project context your AI can query through MCP — with source evidence.

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.

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
Comments