GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Self-hosted Anytype MCP server: the full Anytype API as an always-on Docker + HTTP endpoint.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
ANYTYPE_API_KEY, PORT, ANYTYPE_API_BASE_URL, ANYTYPE_VERSION, ANYTYPE_API_HOST_HEADER, MCP_SHARED_TOKEN, ANYTYPE_MCP_SLIM_RESPONSES标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"anytype": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANYTYPE_API_KEY",
"-e",
"PORT",
"-e",
"ANYTYPE_API_BASE_URL",
"-e",
"ANYTYPE_VERSION",
"-e",
"ANYTYPE_API_HOST_HEADER",
"-e",
"MCP_SHARED_TOKEN",
"-e",
"ANYTYPE_MCP_SLIM_RESPONSES",
"ghcr.io/ohneben/anytype-mcp:1.0.6"
],
"env": {
"ANYTYPE_API_KEY": "your-value",
"PORT": "your-value",
"ANYTYPE_API_BASE_URL": "your-value",
"ANYTYPE_VERSION": "your-value",
"ANYTYPE_API_HOST_HEADER": "your-value",
"MCP_SHARED_TOKEN": "your-value",
"ANYTYPE_MCP_SLIM_RESPONSES": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add anytype --env ANYTYPE_API_KEY=your-value --env PORT=your-value --env ANYTYPE_API_BASE_URL=your-value --env ANYTYPE_VERSION=your-value --env ANYTYPE_API_HOST_HEADER=your-value --env MCP_SHARED_TOKEN=your-value --env ANYTYPE_MCP_SLIM_RESPONSES=your-value -- docker run -i --rm -e ANYTYPE_API_KEY -e PORT -e ANYTYPE_API_BASE_URL -e ANYTYPE_VERSION -e ANYTYPE_API_HOST_HEADER -e MCP_SHARED_TOKEN -e ANYTYPE_MCP_SLIM_RESPONSES ghcr.io/ohneben/anytype-mcp:1.0.6运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"anytype": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANYTYPE_API_KEY",
"-e",
"PORT",
"-e",
"ANYTYPE_API_BASE_URL",
"-e",
"ANYTYPE_VERSION",
"-e",
"ANYTYPE_API_HOST_HEADER",
"-e",
"MCP_SHARED_TOKEN",
"-e",
"ANYTYPE_MCP_SLIM_RESPONSES",
"ghcr.io/ohneben/anytype-mcp:1.0.6"
],
"env": {
"ANYTYPE_API_KEY": "your-value",
"PORT": "your-value",
"ANYTYPE_API_BASE_URL": "your-value",
"ANYTYPE_VERSION": "your-value",
"ANYTYPE_API_HOST_HEADER": "your-value",
"MCP_SHARED_TOKEN": "your-value",
"ANYTYPE_MCP_SLIM_RESPONSES": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"anytype": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANYTYPE_API_KEY",
"-e",
"PORT",
"-e",
"ANYTYPE_API_BASE_URL",
"-e",
"ANYTYPE_VERSION",
"-e",
"ANYTYPE_API_HOST_HEADER",
"-e",
"MCP_SHARED_TOKEN",
"-e",
"ANYTYPE_MCP_SLIM_RESPONSES",
"ghcr.io/ohneben/anytype-mcp:1.0.6"
],
"env": {
"ANYTYPE_API_KEY": "your-value",
"PORT": "your-value",
"ANYTYPE_API_BASE_URL": "your-value",
"ANYTYPE_VERSION": "your-value",
"ANYTYPE_API_HOST_HEADER": "your-value",
"MCP_SHARED_TOKEN": "your-value",
"ANYTYPE_MCP_SLIM_RESPONSES": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
PORT envANYTYPE_API_BASE_URL envANYTYPE_VERSION envANYTYPE_API_HOST_HEADER envANYTYPE_MCP_SLIM_RESPONSES env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 ohneben 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:ANYTYPE_API_KEY, MCP_SHARED_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.6)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Talk to your Anytype knowledge base in plain language from AI assistants like Claude, Cursor, and any other MCP client.
This is a self-hosted fork of the official anyproto/anytype-mcp that adds a Docker container and a Streamable-HTTP transport, so the server can run quietly in the background and be reached by any MCP client over HTTP. (The original speaks stdio only.)
The official Anytype MCP server is great, but it runs as a stdio subprocess that each client has to launch on demand. This project keeps 100% of its capabilities and adds a production-style deployment: one always-on server, in Docker, that any number of MCP clients can reach over HTTP.
| Capability | This project | Official anyproto/anytype-mcp | Other community servers\* |
|---|---|---|---|
| Full Anytype API coverage (dynamic OpenAPI → MCP tools) | ✅ | ✅ | ✅ |
stdio transport | ✅ | ✅ | ✅ |
Streamable-HTTP transport (native, or via mcp-remote) | ✅ | ❌ | ❌ |
| Always-on background service | ✅ | ❌ | ❌ |
| One server → many clients at once | ✅ | ❌ | ❌ |
| Docker + docker-compose | ✅ | ❌ | ❌ |
| Health-check endpoint + auto-restart | ✅ | ❌ | ❌ |
| Optional bearer-token auth on the endpoint | ✅ | ❌ | ❌ |
| 🟢 / 🟡 / 🔴 read-only / write / destructive tool hints | ✅ | ➖ | ➖ |
| Automated test suite (Vitest) | ✅ | ✅ | ➖ |
| License | MIT | MIT | varies |
\*Community servers such as Qwinty/anytype-mcp (JS), wethegreenpeople/anytype-mcp (Python) and anytype-mcp-plus — most are stdio-only and launched via npx. "➖" = not documented / varies. Snapshot from July 2026; check each project for its latest.
In short: if you just want to try Anytype from your AI client, the official server is perfect. If you want it running in the background, always ready, and shared across every MCP client on your machine, use this one.
Once it's connected, ask your assistant things like:
Tools are generated automatically from your running Anytype app and grouped into 🟢 read-only, 🟡 write, and 🔴 delete.
The server is tuned to keep your assistant fast and frugal with tool calls:
space_id, that space's types and property definitions) in a single call, instead of a list-spaces → list-types → list-properties cascade.object discriminators, and nulls are dropped, and the type embedded in each search/list result is reduced to its identifiers. This typically shrinks list/search responses by well over half, which means less context burned per call and fewer follow-up calls. Set ANYTYPE_MCP_SLIM_RESPONSES=false to get raw API payloads instead.get-object returns the full markdown body).Claude / Cursor / … ──MCP──► this server ──HTTP──► Anytype desktop app (local API)
The server only talks to the local API of the Anytype desktop app on your own machine. Your data stays on your computer.
127.0.0.1:31009).1. Add your API key. Copy the example config and paste in a key:
cp .env.example .env
2. Start the server:
docker compose up -d --build
3. Confirm it's running:
curl -s http://localhost:8769/healthz # → {"status":"ok"}
4. Connect your MCP client. Add an anytype entry under mcpServers, then fully quit and reopen the app. Pick the form that matches your client:
Claude Code (or any client that speaks Streamable-HTTP natively) — connect directly, no helper process:
"anytype": {
"type": "http", "url": "http://localhost:8769/mcp" }
Claude Desktop (its config is stdio-only) needs the mcp-remote bridge. Install it once, then launch it via node rather than npx:
npm i -g mcp-remote
"anytype": {
"command": "/opt/homebrew/bin/node", "args": [ "/opt/homebrew/lib/node_modules/mcp-remote/dist/proxy.js", "http://localhost:8769/mcp", "--allow-http" ] }
Why not `npx -y mcp-remote …`?
npxre-resolves the package through the npm
cache on every launch. When a client cold-starts several MCP servers at once they
contend on that cache, and some launchers can wedge *inside npx* for minutes —
which the client reports as a connection timeout. Installing
mcp-remoteonce and
launching it with
noderemoves that step. Use absolute paths (GUI apps don't
inherit your shell
PATH, andmcp-remote's own#!/usr/bin/env nodeshebang
can't find
nodeotherwise). The paths above are Apple-Silicon Homebrew defaults;
adjust with
which nodeandnpm root -gif yours differ.
That's it — ask your assistant to search or create something in Anytype.
In the Anytype desktop app: Settings → API Keys → Create new. Copy the key into .env as ANYTYPE_API_KEY=. Your key stays in .env, which git ignores, so it is never committed.
Everything is set in .env (copied from .env.example):
| Variable | Default | What it does |
|---|---|---|
ANYTYPE_API_KEY | — | Your Anytype API key. Required. |
ANYTYPE_VERSION | 2025-11-08 | Anytype API version header. |
ANYTYPE_API_BASE_URL | http://host.docker.internal:31009 | Where the Anytype app's API is reachable from the container. |
ANYTYPE_API_HOST_HEADER | *(auto)* | Host header sent to the Anytype API. Auto-set to localhost: when the base URL uses a container host alias, because Anytype rejects any other Host with 403 request origin is not allowed. |
PORT | 8769 | Host port for the MCP endpoint. |
MCP_SHARED_TOKEN | *(empty)* | Optional bearer token to protect the endpoint. Empty = open, for localhost only. |
ANYTYPE_MCP_SLIM_RESPONSES | true | Compact API responses before sending them to the assistant. Set to false for raw payloads. |
After changing .env, reload with docker compose up -d --force-recreate.
For logs, restart, key rotation, and verification commands, see [DOCKER.md](./DOCKER.md).
Prefer the classic stdio mode? Build it locally:
npm install
npm run build
Then register it with your client using a stdio command and your key in OPENAPI_MCP_HEADERS — see the upstream README for the exact stdio configuration.
.env, which is git-ignored. Never commit real keys.MCP_SHARED_TOKEN and send it as a Bearer header or ?token=….This server publishes to the official MCP Registry under the name io.github.ohneben/anytype-mcp. To look up the current listing:
curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.ohneben/anytype-mcp"
Its listing is described by server.json and is republished automatically on every v*.*.* tag by .github/workflows/publish-mcp.yml, which waits for the matching GHCR image and authenticates with GitHub OIDC (no secret needed). The registry proves the image is ours via the io.modelcontextprotocol.server.name label in the Dockerfile, so the GHCR package must stay Public.
The git tag is the version. Pushing v1.2.3 is the whole release: the tag is stamped into package.json before the image is built and into server.json before the listing is published, so the version the server reports to MCP clients, the image tag, and the registry entry cannot disagree. Nothing needs to be bumped by hand first, and the versions committed here are only the defaults used by local builds.
Built on the official Anytype MCP server by Any Association. Licensed under the MIT License.