Affine
FreeNot checkedModel Context Protocol server for AFFiNE. Connect AI assistants to AFFiNE workspaces, documents, databases, and collaboration APIs over stdio or HTTP.
About
Model Context Protocol server for AFFiNE. Connect AI assistants to AFFiNE workspaces, documents, databases, and collaboration APIs over stdio or HTTP.
README
A Model Context Protocol (MCP) server for AFFiNE. It exposes AFFiNE workspaces and documents to AI assistants over stdio (default) or HTTP (/mcp) and supports both AFFiNE Cloud and self-hosted deployments.
Table of Contents
- Overview
- Choose Your Path
- Quick Start
- Compatibility Matrix
- Tool Surface
- Documentation Map
- Verify Your Setup
- Security and Scope
- Development
- Release Notes
- License
- Support
Overview
AFFiNE MCP Server is designed for three common scenarios:
- Run a local stdio MCP server for Claude Code, Codex CLI, Cursor, or Claude Desktop
- Expose a remote HTTP MCP endpoint for hosted or browser-connected clients
- Automate AFFiNE workspace, document, database, organization, and comment workflows through a stable MCP tool surface
Highlights:
- Supports AFFiNE Cloud and self-hosted AFFiNE instances
- Supports stdio and HTTP transports
- Supports session-cookie and email/password authentication, plus compatible bearer tokens for older deployments
- Exposes 92 canonical MCP tools backed by AFFiNE GraphQL and WebSocket APIs
- Includes semantic page composition, native template instantiation, database intent composition, capability and fidelity reporting, and workspace blueprint helpers
- Includes Docker images, health probes, and end-to-end test coverage
Scope boundaries:
- This server can access only server-backed AFFiNE workspaces
- Browser-local workspaces stored only in local storage are not available through AFFiNE server APIs
- AFFiNE 0.27+ removed the legacy personal-access-token GraphQL API; this server no longer exposes token-management tools
- AFFiNE Cloud requires browser-session authentication for this external GraphQL integration; programmatic email/password sign-in is blocked by Cloudflare
New in v3.1.0: Workspace discovery now includes profile metadata and direct links, with improved authentication and document deletion compatibility for AFFiNE 0.27.3.
Choose Your Path
| Goal | Start here |
|---|---|
| Set up a local stdio server with the least friction | docs/getting-started.md |
| Run the server in Docker or another OCI runtime | docs/getting-started.md#path-c-run-from-the-docker-image |
| Configure Claude Code, Claude Desktop, Codex CLI, or Cursor | docs/client-setup.md |
| Run the server remotely over HTTP or behind OAuth | docs/configuration-and-deployment.md |
| Lock down tool exposure for least-privilege deployments | docs/configuration-and-deployment.md#least-privilege-tool-exposure |
| Learn common AFFiNE workflows and tool sequences | docs/workflow-recipes.md |
| Browse the tool catalog by domain | docs/tool-reference.md |
Quick Start
1. Install the CLI
npm i -g affine-mcp-server
affine-mcp --version
You can also run the package ad hoc:
npx -y -p affine-mcp-server affine-mcp -- --version
2. Or run the server in Docker
docker run -d \
-p 3000:3000 \
-e MCP_TRANSPORT=http \
-e AFFINE_BASE_URL=https://your-affine-instance.com \
-e [email protected] \
-e AFFINE_PASSWORD=your-password \
-e AFFINE_MCP_AUTH_MODE=bearer \
-e AFFINE_MCP_HTTP_TOKEN=your-strong-secret \
ghcr.io/dawncr0w/affine-mcp-server:latest
Then point your client at:
{
"mcpServers": {
"affine": {
"type": "http",
"url": "http://localhost:3000/mcp",
"headers": {
"Authorization": "Bearer your-strong-secret"
}
}
}
}
For Docker, health checks, and remote deployment details, see docs/configuration-and-deployment.md#docker.
3. Save credentials with interactive login
affine-mcp login
This stores credentials in $XDG_CONFIG_HOME/affine-mcp/config when XDG_CONFIG_HOME is set, otherwise in ~/.config/affine-mcp/config, with mode 600.
- For AFFiNE Cloud, paste the Cookie request header from a signed-in browser session
- For self-hosted AFFiNE, use email/password (recommended) or a signed-in session cookie
AFFINE_API_TOKENremains available only for deployments that still accept a compatible GraphQL bearer token
4. Register the server with your client
Claude Code project config:
{
"mcpServers": {
"affine": {
"command": "affine-mcp"
}
}
}
Codex CLI:
codex mcp add affine -- affine-mcp
More client-specific setup is in docs/client-setup.md.
5. Verify the connection
affine-mcp status
affine-mcp doctor
If you want to expose the server remotely over HTTP instead of stdio, start with docs/configuration-and-deployment.md.
Compatibility Matrix
Node.js 20 is the minimum supported runtime. CI validates the minimum runtime and the current Node.js release used by the npm publish workflow.
| Target | Transport | Recommended auth | Recommended path |
|---|---|---|---|
| Claude Code | stdio | Saved config | docs/client-setup.md#claude-code |
| Claude Desktop | stdio | Saved config or session cookie | docs/client-setup.md#claude-desktop |
| Codex CLI | stdio | Saved config or self-hosted email/password | docs/client-setup.md#codex-cli |
| Cursor | stdio | Saved config or session cookie | docs/client-setup.md#cursor |
| Containerized remote deployment | HTTP | Bearer token or OAuth | docs/getting-started.md#path-c-run-from-the-docker-image |
| Remote MCP clients | HTTP | Bearer token or OAuth | docs/configuration-and-deployment.md#http-mode |
| AFFiNE Cloud | stdio or HTTP | Signed-in browser session cookie | docs/configuration-and-deployment.md#auth-strategy-matrix |
| Self-hosted AFFiNE | stdio or HTTP | Email/password or session cookie | docs/configuration-and-deployment.md#auth-strategy-matrix |
Tool Surface
tool-manifest.json is the source of truth for canonical tool names. The MCP server exposes those tools through tools/list and tools/call; tool definitions returned by tools/list include MCP annotations that mark read-only, destructive, idempotent, and external-world behavior for client-side tool selection.
Domains:
- Workspace: create, inspect, update, delete, and traverse workspaces
- Organization: collections, collection-rule sync, workspace blueprints, and experimental organize or folder helpers
- Documents: search, read, create, publish, move, tag, custom properties, import/export, semantic composition, template inspection and native instantiation, capability and fidelity reporting, and block-level mutation
- Databases: create columns, add rows, update rows, inspect schema, and compose database structures from intent
- Comments: list, create, update, delete, and resolve
- History: version history listing
- Users and authentication: current user, sign-in, and profile/settings
- Notifications: list and mark notifications as read
- Blob storage: upload, delete, and cleanup blobs
Use AFFINE_TOOL_PROFILE=read_only, core, or authoring when a deployment should expose a smaller surface than the complete full default. This is the recommended path for hosted, browser-connected, or least-privilege deployments because it reduces agent choice overload while keeping the full tool catalog available as an opt-in surface. You can also combine profiles with AFFINE_DISABLED_GROUPS such as docs.database, destructive, or admin for finer control.
For the grouped catalog, notes, and operational caveats, see docs/tool-reference.md.
Documentation Map
| Document | Purpose |
|---|---|
| docs/getting-started.md | First-run setup paths and verification |
| docs/client-setup.md | Client-specific configuration snippets and tips |
| docs/configuration-and-deployment.md | Environment variables, auth modes, Docker, HTTP mode, and deployment guidance |
| docs/workflow-recipes.md | End-to-end workflows and example tool sequences |
| docs/tool-reference.md | Tool catalog grouped by domain |
| docs/edgeless-canvas-cookbook.md | Edgeless canvas layout helpers and surface elements, worked end-to-end |
| CONTRIBUTING.md | Contributor workflow |
| SECURITY.md | Security reporting |
Verify Your Setup
Useful CLI commands:
affine-mcp status- test the effective configurationaffine-mcp status --json- machine-readable status outputaffine-mcp doctor- diagnose config and connectivity issuesaffine-mcp show-config- print the effective config with secrets redactedaffine-mcp config-path- print the config file pathaffine-mcp snippet <claude|cursor|codex|all> [--env]- generate ready-to-paste client configaffine-mcp logout- remove stored credentials
status, doctor, and the server runtime use the same environment > saved config > defaults resolution. For a self-hosted deployment with a non-standard GraphQL route, use affine-mcp login --graphql-path /your/graphql/path or set AFFINE_GRAPHQL_PATH; show-config --json prints the exact resolved graphqlEndpoint without exposing secrets.
For common failures, see:
- docs/getting-started.md#common-first-run-failures
- docs/configuration-and-deployment.md#deployment-checklist
Security and Scope
- Never commit passwords, session cookies, or compatible bearer tokens
- Use a dedicated least-privilege AFFiNE account for unattended deployments
- Email/password HTTP sessions share one login and never fall back to anonymous backend requests after authentication failure
- Use HTTPS for non-local deployments
- Keep remote HTTP MCP listeners authenticated; bearer mode refuses a non-loopback bind without
AFFINE_MCP_HTTP_TOKEN - Send MCP bearer tokens in the
Authorizationheader, never in the URL - Re-run
affine-mcp loginwhen a saved browser session expires - Restrict exposed tools with
AFFINE_DISABLED_GROUPSandAFFINE_DISABLED_TOOLSfor least-privilege setups - Treat OAuth mode as a shared AFFiNE service-account deployment: it defaults to
read_only, and write-capable profiles requireAFFINE_OAUTH_ALLOW_SERVICE_WRITES=true - Use
/healthzand/readyzwhen running the HTTP server behind a container platform or load balancer - Set HTTP body, session, idle, and shutdown limits explicitly for high-volume deployments
Development
Run the main quality gates before opening a PR:
npm run ci
Additional validation:
npm testverifies tool metadata, test-suite coverage, and the fast regression suite without requiring a live AFFiNE instancenpm run test:comprehensiveboots a local Docker AFFiNE stack and validates the tool surfacenpm run test:e2eruns Docker, MCP, and Playwright togethernpm run test:playwrightruns the Playwright suite only- Focused runners for the new high-level tool surface include
npm run test:create-placement,npm run test:capabilities-fidelity,npm run test:native-template,npm run test:mutation-ack,node tests/test-database-intent.mjs,node tests/test-semantic-page-composer.mjs,node tests/test-structured-receipts.mjs,node tests/test-organize-tools.mjs, andnode tests/test-supporting-tools.mjs
Live tests can mutate or delete AFFiNE data. They allow loopback targets by
default and refuse non-loopback targets unless the disposable target is
explicitly enabled and confirmed as documented in CONTRIBUTING.md. Never run
them against production.
Local clone flow:
git clone https://github.com/dawncr0w/affine-mcp-server.git
cd affine-mcp-server
npm install
npm run build
node dist/index.js
Release Notes
License
MIT License - see LICENSE.
Support
- Open an issue on GitHub
- Review AFFiNE product documentation at docs.affine.pro
Acknowledgments
- Built for the AFFiNE knowledge base platform
- Uses the Model Context Protocol specification
- Powered by @modelcontextprotocol/sdk
Installing Affine
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/DAWNCR0W/affine-mcp-serverFAQ
Is Affine MCP free?
Yes, Affine MCP is free — one-click install via Unyly at no cost.
Does Affine need an API key?
No, Affine runs without API keys or environment variables.
Is Affine hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Affine in Claude Desktop, Claude Code or Cursor?
Open Affine on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare Affine with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
