Skip to main content
MCP server CX Codex

AppFlowy MCP Server — Claude Code MCP server: what it does

MCP server for Claude Code and Cursor that connects AI agents to your AppFlowy workspace. Runs locally via Docker or uvx before starting a session with environment variables.

MIT ★ 9 updated 2026-11-14

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add --env APPFLOWY_BASE_URL=<APPFLOWY_BASE_URL> --env APPFLOWY_EMAIL=<APPFLOWY_EMAIL> --env APPFLOWY_PASSWORD=<APPFLOWY_PASSWORD> --env APPFLOWY_ACCESS_TOKEN=<APPFLOWY_ACCESS_TOKEN> --env ALLOWED_WORKSPACE_IDS=<ALLOWED_WORKSPACE_IDS> --transport stdio appflowy-mcp-server -- docker run -i --rm -e APPFLOWY_BASE_URL -e APPFLOWY_EMAIL -e APPFLOWY_PASSWORD -e APPFLOWY_ACCESS_TOKEN -e ALLOWED_WORKSPACE_IDS ghcr.io/rahulk644/appflowy-mcp-server:2.2.0
Open on GitHub

What AppFlowy MCP Server does

AppFlowy MCP Server connects AI assistants to your AppFlowy workspace to edit Markdown documents, manage typed database rows, board cards, and pages. The server exposes 11 async tools for keyword search, batch record creation, and importing or export of document trees.

Operation requires an AppFlowy bot account, workspace identifiers, and credentials via email and password or an APPFLOWY_ACCESS_TOKEN. Without a configured .env file granting workspace access, the server rejects incoming connections.

The package supports local stdio transport or an authenticated HTTP service. The configuration uses Docker images or the uvx launcher with a built-in doctor command for diagnostics.

Tested against the self-hosted Cloud 0.21.4 and Web 0.20.12 baseline.

What it helps with

  • edit Markdown documents and pages
  • update typed database rows and board cards
  • search workspace pages by keywords
  • export and import document trees

Example prompts for the agent

  • Find the project brief in AppFlowy and append the task checklist
  • Move an existing board card to Done status
  • Create a database with tracking fields and add typed rows

How to install AppFlowy MCP Server

Platform CLI

claude mcp add --env APPFLOWY_BASE_URL=<APPFLOWY_BASE_URL> --env APPFLOWY_EMAIL=<APPFLOWY_EMAIL> --env APPFLOWY_PASSWORD=<APPFLOWY_PASSWORD> --env APPFLOWY_ACCESS_TOKEN=<APPFLOWY_ACCESS_TOKEN> --env ALLOWED_WORKSPACE_IDS=<ALLOWED_WORKSPACE_IDS> --transport stdio appflowy-mcp-server -- docker run -i --rm -e APPFLOWY_BASE_URL -e APPFLOWY_EMAIL -e APPFLOWY_PASSWORD -e APPFLOWY_ACCESS_TOKEN -e ALLOWED_WORKSPACE_IDS ghcr.io/rahulk644/appflowy-mcp-server:2.2.0

Replace <…> with your own values. 1 more environment variable is in the server README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about AppFlowy MCP Server

How to install AppFlowy MCP Server in Claude Code?

Run `claude mcp add --env APPFLOWY_BASE_URL=<APPFLOWY_BASE_URL> --env APPFLOWY_EMAIL=<APPFLOWY_EMAIL> --env APPFLOWY_PASSWORD=<APPFLOWY_PASSWORD> --env APPFLOWY_ACCESS_TOKEN=<APPFLOWY_ACCESS_TOKEN> --env ALLOWED_WORKSPACE_IDS=<ALLOWED_WORKSPACE_IDS> --transport stdio appflowy-mcp-server -- docker run -i --rm -e APPFLOWY_BASE_URL -e APPFLOWY_EMAIL -e APPFLOWY_PASSWORD -e APPFLOWY_ACCESS_TOKEN -e ALLOWED_WORKSPACE_IDS ghcr.io/rahulk644/appflowy-mcp-server:2.2.0`.

What does AppFlowy MCP Server do?

It bridges AI clients with your AppFlowy workspace, giving agents tools to read, create, and modify Markdown documents, databases, and project boards.

What is required to run AppFlowy MCP Server?

It requires Python 3.11+ or Docker, an AppFlowy bot account with workspace permissions, and environment variables defined in a .env file.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open