DAWNCR0W/affine-mcp-server

Model Context Protocol server for AFFiNE. Connect AI assistants to AFFiNE workspaces, documents, databases, and collaboration APIs over stdio or HTTP.

What it solves

This project acts as a bridge between the AFFiNE productivity platform and AI assistants. It allows AI models (like those in Claude Desktop, Cursor, or Codex) to read, write, and manage your AFFiNE workspaces, documents, databases, and comments directly through the Model Context Protocol (MCP).

How it works

The server connects to your AFFiNE instance (either Cloud or self-hosted) using your credentials. It exposes over 100 tools via the MCP standard, which AI agents can then call to perform tasks such as creating pages, updating database rows, or searching through your notes. It supports two modes: a local stdio mode for desktop AI tools and an HTTP mode for remote or containerized deployments.

Who it’s for

It is designed for power users and developers who want to integrate their AI agents directly into their AFFiNE workflow, enabling automated document creation, database management, and workspace organization.

Highlights

  • Supports both AFFiNE Cloud and self-hosted deployments.
  • Provides over 100 canonical MCP tools for comprehensive workspace management.
  • Offers flexible authentication, including session cookies and email/password for self-hosted instances.
  • Includes robust configuration options for least-privilege access, such as read-only profiles and disabled tool groups.
  • Features built-in support for Docker and health monitoring for remote server deployments.

Related

  • Project
    workopia/workopia-mcp

    A hosted MCP server that integrates job searching, resume tailoring, and application tracking into AI assistants like Claude and Cursor.

  • Project
    nicobailon/pi-interview-tool

    pi-interview-tool is a custom tool for pi-agent that opens an interactive form to gather user responses to clarification questions. It supports multiple question types, rich media, recommendations, auto-save, and session recovery.

  • Project
    Prompthon-IO/agent-systems-handbook

    A field guide to understanding, designing, building, and operating production-ready AI agent systems, mapping workflows, tools, memory, and multi-agent architecture.

  • Project
    jd-opensource/JoySafeter

    An AI-native platform for building and orchestrating security agents to automate complex tasks like vulnerability analysis and penetration testing.