Brain Memory
概览
作者提供的说明(英文原文)
Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.
它能帮你做什么
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。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 搜索与 AI 记忆
安装
选择你使用的 AI 应用,然后复制设置。
通过 4/5 项检查 · 你的提问会经过开发者的服务器(mcp.brainmemory.ai)
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个
打开 Claude 的 Connectors 页面
CustomizeConnectors
点击“+ Add” → “Add custom connector”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Name · 名称Brain MemoryRemote MCP server URL · 地址https://mcp.brainmemory.ai/mcpAuthentication 保持 Claude 检测到的设置,然后点击 Add
在聊天中开启
+ConnectorsBrain Memory
试一试
用 Brain Memory 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Brain Memory,或回答中出现 Brain Memory 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
仅企业版 ChatGPT 可连接
适用于网页版 ChatGPT Business、Enterprise 或 Edu,需由工作区管理员或所有者添加 · 使用 Free、Plus 或 Pro:你的 ChatGPT 方案暂时无法自行连接 MCP
在网页版 ChatGPT 打开添加 MCP 的页面
Plugins+Add custom MCP server
填写名称和地址
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Name · 名称Brain MemoryConnection · 地址https://mcp.brainmemory.ai/mcp在聊天中选择 Brain Memory
开启新聊天,输入前先从插件列表中选择 Brain Memory
试一试
用 Brain Memory 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Brain Memory,或回答中出现 Brain Memory 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --transport http brain https://mcp.brainmemory.ai/mcp在 Claude Code 中输入 /mcp
应能看到 Brain Memory 在列表中并显示已连接
试一试
用 Brain Memory 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Brain Memory,或回答中出现 Brain Memory 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 Brain Memory 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Brain Memory,或回答中出现 Brain Memory 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 Brain Memory 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Brain Memory,或回答中出现 Brain Memory 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://mcp.brainmemory.ai/mcpJSON 设置在下方“开发者专用”中
开发者专用:终端命令和 JSON 设置
通过网页连接
Claude Code
claude mcp add --transport http brain https://mcp.brainmemory.ai/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"brain": {
"url": "https://mcp.brainmemory.ai/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"brain": {
"type": "http",
"url": "https://mcp.brainmemory.ai/mcp"
}
}
}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。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
它能做什么
服务器要求先登录,才会列出它的工具。
基础检查i
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11日
- ! 注意
作者与仓库一致
发布者(brainmemory.ai)不是仓库所有者(omelas-tech);可能是其他人代为上架的
- ✓ 通过
仍在维护
代码最后更新于昨天
- ✓ 通过
有许可证
使用 MIT
- ✓ 通过
端点有响应
在 72 毫秒内响应(HTTP 401)
- ✓ 通过
使用 OAuth 登录
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
- … 尚未检查
工具描述中没有隐藏指令
尚未检查;我们会在检查端点时读取工具列表
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 5911 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 5911 个服务器的 89% 更新
- 基础检查结果等于或优于此分类中其他 5911 个服务器的 50%
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。
常见问题
Brain Memory 安全吗?
它在 5 项适用的基础检查中通过了 4 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。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于昨天,最新版本(0.5.1)于4天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于支持远程 MCP 的应用,例如 ChatGPT Business 及以上方案。
有什么可以替代它?
同一分类中有:Ruflo, Context7, Metabase
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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
作者的 README
打开 README
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。
brain-connector
The Brain Memory Claude connector — a remote MCP server that exposes the brain's scored recall to Claude (web / desktop / iOS / Cowork). Built with the official @modelcontextprotocol/sdk per Anthropic's build-mcp-server guidance. Design rationale lives in brain-cloud/docs/connector-architecture.md.
It lives in this repo (not the npm package — excluded from package.json files, like website/) so it reuses the real recall engine in ../src directly. One brain, one engine, two faces.
Status: 🟢 LIVE IN PRODUCTION — Phase 1 + 2 (read + write)
Deployed at `https://mcp.brainmemory.ai/mcp` (Node service on the VPS beside brain-cloud; systemd + nginx + certbot — see deploy/). Added at claude.ai and verified on Claude web + iPhone. Tools: brain_recall, brain_status (read) + brain_memorize, brain_pin, brain_unpin, brain_forget, brain_verify (write — writes sync back to brain-cloud; hosts gate them behind confirmation) + brain_use (switch between the account's brains).
Two things to know in production:
- One brain ↔ one Google account — the connector serves the brain of whatever Firebase (Google) identity signs in, so the brain must be pushed to *that* brain-cloud account. See Identity & accounts below for how the connector now surfaces a wrong / empty / multi-brain account instead of silently serving a phantom brain.
- Sessions renew silently for ~a month — access tokens live 1 h, but the token endpoint issues rotating refresh tokens (OAuth 2.1: single-use, family-revoked on reuse) with a sliding 30-day window (
CONNECTOR_REFRESH_TTL_MS), so an active user never sees the login page. Each refresh also renews the Firebase credential server-side (securetoken API, from the refresh token captured at login) — so sync-back and TTL re-pulls keep working far past the old ~1 h Firebase ID-token window. Grants + the DCR client registry persist underCONNECTOR_STATE_DIR(systemdStateDirectory; Firebase refresh tokens encrypted at rest viaCONNECTOR_STATE_KEY, our tokens stored hashed), so deploys/restarts no longer log users out. Local CLI memories (brain cloud push) reach an active session automatically via a TTL re-pull (CONNECTOR_REPULL_TTL_MS, default 120s) — it re-pulls only when the cloud checksum changed and never over an unsynced local write.
npm test typechecks and proves the whole path end-to-end in one server — the complete OAuth 2.1 handshake through to real scored recall (token request is form-urlencoded, matching real clients):
① unauthenticated MCP call → 401 + WWW-Authenticate (RFC 9728)
② discovery → AS metadata (RFC 8414), PKCE S256 ③ Dynamic Client Registration (RFC 7591) ④ authorize → code (iss + state validated, RFC 9207) ⑤ token → audience-bound Bearer (PKCE verified, RFC 8707) ⑥ MCP initialize + tools/list → [brain_recall, brain_status, brain_use, brain_memorize, brain_pin, brain_unpin, brain_forget, brain_verify] (official SDK) ⑦ brain_recall(query) → the brain's REAL scored results (relevance + decayed strength + spreading activation), identical to the CLI
How recall stays identical to the CLI
The engine bridge (src/engine.ts) runs the repo's bin/recall.js with BRAIN_DIR pointed at the authenticated user's brain working copy — so the connector's scoring is byte-for-byte the CLI's, with zero reimplementation. (BRAIN_DIR is the same override the CLI ships.)
Run / test
npm install
npm test # end-to-end Phase 1 proof npm start # serve MCP on http://localhost:8788
Tools
| Tool | Kind | Description |
|---|---|---|
brain_recall | read (readOnlyHint) | Ranked recall for a query, scored by the brain engine. |
brain_status | read (readOnlyHint) | Memory count + last-updated for the user's brain, and the account's brains with the one in use marked active. |
brain_use | write (idempotentHint) | Switch which of the account's brains the connector serves, by name or id. Remembered across sessions; copies nothing between brains. |
brain_memorize | write (destructiveHint) | Store the explicit content provided (never the conversation); immediately recallable. |
brain_pin / brain_unpin | write (destructiveHint, idempotentHint) | Move a memory into or out of the always-present tier. |
brain_forget | write (destructiveHint) | Archive a memory (recoverable — moved to _archived/, not hard-deleted). |
brain_verify | write (destructiveHint) | List memories pending verification; approve them, or reject them into the archive. |
Writes reuse the deterministic CLIs (memorize.js / pin.js / unpin.js / forget.js) and then syncBack() to brain-cloud.
Identity & accounts
One brain ↔ one Google account. The connector has no idea which laptop you're on — it serves the brain belonging to whatever Firebase (Google) identity completes the sign-in. The verified uid maps deterministically to a brain user (resolveBrainUserId), and that user's canonical brain is pulled from brain-cloud: the brain the user chose with brain_use, or else the account's oldest. So the rule is simple: connect with the same Google account your CLI's `brain cloud` syncs to, and use the same brain (brain cloud brains shows which one the CLI is linked to).
To keep that rule from failing silently, ensureUserBrain returns an identity signal that the tools surface to you:
| Situation | identity.status | What you see |
|---|---|---|
| Account has no brain in Brain Cloud | no-cloud-brain | A note (in brain_status, and in brain_recall when it finds nothing) telling you this account is empty — most likely you signed in with the wrong Google account, or you're brand new. |
| Account has exactly one brain | ok | Nothing — the common, unambiguous case. |
| Account has several brains | multiple-brains | A note naming the brain in use. brain_status lists them all; brain_use switches, and the choice (kept with the OAuth state, per user) holds for later sessions. A chosen brain that is later deleted falls back to the oldest. |
This is *guidance, not enforcement* — a genuinely new user with no brain yet still gets a usable empty brain. Account-linking (letting one Google identity span several brains at once) is deliberately deferred; choosing one brain at a time is brain_use.
Auth
Two layers — both real now:
- OAuth 2.1 between Claude and the connector (
src/oauth.ts): authorize / token / register / metadata, PKCE S256, RFC 8707 audience binding, RFC 9207iss. Tokens mint intosrc/auth.ts's store; the/mcpguard validates them (incl. audience). - Who is the human (
src/firebase.ts):/authorizebounces the user through Firebase login (the same project brain-cloud uses). The connector verifies the ID token server-side and secret-free — RS256 against Google's public certs, checkingaud/iss/exp— so it needs only the public project config, no service-account key. The verifieduidmaps to the brain user, then the OAuth code is minted.
If FIREBASE_* env is not set, /authorize falls back to a fixed dev user (STUB:FIREBASE) so the headless test runs without a browser.
See the Firebase login work (demo)
cp .env.example .env # fill in FIREBASE_API_KEY / AUTH_DOMAIN / PROJECT_ID
npm start # http://localhost:8788
then connect an MCP client (e.g. Claude) to http://localhost:8788/mcp —
the OAuth flow opens the branded Google sign-in page from /authorize
Signing in through /authorize shows the branded consent/login page and, on success, resolves your verified firebase_uid → brain_user_id → brain_dir — which is how the connector picks whose brain to serve. (localhost is an authorized Firebase domain by default, so popup sign-in works locally.)
Per-user store (src/store.ts)
ensureUserBrain({ userId, brainDir, idToken }) populates the user's brain working copy from a pluggable provider, then the engine recalls over it. Providers (via CONNECTOR_STORE, else inferred):
- `brain-cloud` (production) — pulls the user's
{brainID}.tar.gzfromBRAIN_CLOUD_API_URL(defaulthttps://api.brainmemory.ai) using their Firebase ID token (brain-cloud's middleware accepts it directly), thentar xzfintobrainDir. Refreshed at each login. - `local` (dev) — symlinks
brainDir→$DEV_LOCAL_BRAIN(your live~/.brain), so your machine serves your real brain through the connector. - `none` — assume pre-provisioned (tests).
Always graceful: if the brain is still missing, it empty-inits a valid (recall-safe) brain.
The brain-cloud provider speaks the store contract, so it works against any store that implements it, including a self-hosted brain-store. Sync-back is conditional (If-Match): if another device pushed first, the connector discards its working copy, starts again from the store's brain, re-applies the write and pushes again, so nobody's memories are overwritten.
Identity providers (src/identity.ts)
Who is logging in, and what the connector presents to the store for them, sits behind one interface. Select with CONNECTOR_IDP:
- `firebase` (the default when
FIREBASE_*is set) — Google sign-in. The store credential is the Firebase ID token, renewed from the Firebase refresh token. - `static` — for a self-hosted store. The sign-in page takes the token the store's operator issued (
brain-store user add); the store decides who the user is. RequiresBRAIN_CLOUD_API_URLto be set explicitly, so a token can never be sent to the hosted default by accident. Rotating or removing the user at the store ends their sessions at the next silent renewal.
- `oidc` — for a self-hosted store that accepts your organisation's OpenID Connect issuer (Entra, Google Workspace, Keycloak, Okta).
/authorizesends the browser to the issuer (authorization code + PKCE + nonce) and the issuer returns it to/oidc/callback. The ID token is the store credential, renewed from the issuer's refresh token. NeedsOIDC_ISSUER,OIDC_CLIENT_IDand an explicitBRAIN_CLOUD_API_URL. Token verification is the store's own (store/lib/oidc.js), so the two can never disagree about what a valid token is. An issuer outage answers503and keeps the login; a revocation ends it.
With no provider configured the connector refuses to start in production. When the reverse proxy is not on loopback (another container, say), name it with CONNECTOR_TRUST_PROXY, for example uniquelocal; true is refused.
Next
- Account-linking — let one user span several brains at once (recall across them), rather than serving one chosen brain at a time. See Identity & accounts.
- Directory submission — remaining manual steps (test account, MCPB packaging, launch post); see the submission checklist in
brain-cloud/docs/connector-architecture.md§7.