
Second Brain Bridge
io.github.IsaiahDupree由 GitHub 账号 IsaiahDupree 发布v1.3.0更新于 Oct 24, 2026
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
发布方自己的服务:BrainDog
概览
把 ChatGPT 连接到你自己 Mac 上的 Obsidian 风格 Markdown 笔记库,可搜索、读取并基于笔记回答问题。
- 可以做什么
- 按关键词搜索笔记库并返回排序后的片段
- 基于自己的笔记回答问题
- 按标题或 id 读取完整笔记,并列出笔记库中的文件夹或来源
- 显示通过 wikilink 链接到某篇笔记的其他笔记(Pro)
- 在笔记库中新建 Markdown 笔记(Pro)
- 查看当前套餐与升级链接
- 适用场景
- 适合在 Mac 上以 Markdown 笔记库形式保存笔记、并希望 ChatGPT 直接检索和推理这些内容而不把整个笔记库上传到第三方知识库的人。适用于个人资料查找、回顾过往决定以及从对话中起草新笔记。
- 运行要求
- 需要远程 MCP 端点并通过 OAuth 登录,还需注册账号并生成配对码。Mac 上须安装本地 Node 代理(Node 18+,私有索引需 Node 22.13+),保持运行,并通过 SECONDBRAIN_VAULT 或代理配置文件指向笔记库目录。Mac 需保持唤醒且代理在线;macOS 可能一次性请求“文件与文件夹”访问权限。
安装
在 SourceWeft 中
- 打开 控制台中的 Second Brain Bridge,将其添加到工作区。
- 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
- 为需要使用其工具的对话启用该服务。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
交给智能体安装
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.IsaiahDupree%2Fsecond-brain-bridge/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。其他 MCP 客户端
把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。
{
"mcpServers": {
"second-brain-bridge": {
"type": "http",
"url": "https://secondbrainbridge.vercel.app/mcp"
}
}
}README
🧠 SecondBrainBridge
Your Obsidian vault, searchable and reasoned over — inside ChatGPT, from your own Mac.
SecondBrainBridge is a Model Context Protocol (MCP) connector that lets ChatGPT search and reason over your Obsidian-style Markdown vault — a folder of notes on your Mac. Reads execute locally and requested results pass through the authenticated relay — every action runs on your own Mac through a tiny local agent. The cloud piece is only a stateless relay that shuttles requests between ChatGPT and your Mac.
Your Mac is the only place your notes are ever read or written. The relay stores only short-lived job payloads and your account record; it never sees note content unless a job is in flight, and jobs expire in seconds.
For users — 3 steps
1. Create your account at secondbrainbridge.vercel.app and generate a pairing code.
2. Install the Mac agent (needs Node 18+):
Point it at your vault folder — set SECONDBRAIN_VAULT=/path/to/your/vault, or save the path in ~/.secondbrainbridge-agent.json. The first time the agent reads a vault kept in a protected location (Documents, Desktop, or iCloud Drive), macOS asks once for Files-and-Folders access — click OK.
3. Connect ChatGPT: Settings → Plugins → turn on Developer mode (Security & login) → Create a custom plugin → paste the MCP Server URL https://secondbrainbridge.vercel.app/mcp → Authentication OAuth → sign in & Allow.
That's it. In a new chat: "Search my notes for the Q3 planning doc" or "What did I decide about Project Atlas?"
Your Mac must be awake with the agent running.
npx second-brain-agent installmakes it start automatically at login and restart if it ever crashes.
Managing the agent
What ChatGPT can do
Retrieval is v1 ranked keyword + title match, so answers stay grounded in the passages that actually appear in your notes. (Semantic/cloud ranking is a Pro/cloud enhancement.)
Plans
SecondBrainBridge is free to start. Upgrade to Pro when you want the full graph and write access.
Billing is handled by Stripe. Upgrade at secondbrainbridge.vercel.app/upgrade, and run get_plan in any chat to see your current plan plus an upgrade link. The relay enforces the Free daily cap and gates the Pro tools by your Stripe subscription (test mode for now).
Self-hosting
You can run your own relay so nothing depends on the hosted instance.
Prereqs: a Vercel account and a Supabase project (free tiers are fine).
- Storage — in your Supabase project's SQL editor, run
supabase/schema.sql. It creates a tiny Redis-shaped KV + queue surface (nb_*functions) with RLS on. - Deploy the
server/directory to Vercel. - Set env vars (see
server/.env.example):SUPABASE_URL,SUPABASE_SERVICE_ROLE_KEY— your project + service-role keyJWT_SECRET—openssl rand -hex 32STRIPE_SECRET_KEY,STRIPE_WEBHOOK_SECRET— for the Pro tier (optional; Free-only if omitted)
- Verify:
curl https://YOUR-APP.vercel.app/api/health→redisConfigured,redisOk,jwtSecretSetalltrue. - Point the agent at it:
npx second-brain-agent pair <CODE> --server https://YOUR-APP.vercel.app.
How it works
- Auth — OAuth 2.1 with PKCE and Dynamic Client Registration (RFC 7591). ChatGPT registers itself, the user signs in on the SecondBrainBridge consent page, and ChatGPT gets a scoped MCP access token. JWTs are HMAC-signed; three kinds (
session,agent,mcp) with distinct privileges. Optional email verification via Resend (RESEND_API_KEY); off unless configured, and enforcement is opt-in (REQUIRE_EMAIL_VERIFICATION). - Relay — MCP tool call → job pushed to
jobs:<user>(TTL ≤ the caller's wait window, so an abandoned job can't run late) → the Mac agent (holding a hanging long-poll) is handed the job within ~200ms, executes it, pushes the result → the MCP handler returns it. The long-poll means jobs are delivered on arrival rather than on a fixed interval, so relay overhead is ~300ms instead of ~1s. The agent is considered "online" only while it's actively connected. The relay also enforces the Free daily search cap and unlocks the Pro tools based on the account's Stripe subscription. - Agent — a dependency-free Node CLI. It indexes the Markdown files in your vault folder and answers retrieval queries locally (ranked keyword + title match);
create_notewrites a new Markdown file into the vault. Reads and writes happen straight against the filesystem — the first touch of a protected folder triggers the one-time macOS Files-and-Folders prompt. A macOS LaunchAgent keeps it alive across logins and crashes.
Repository layout
Development
Security & privacy
- Notes are read/written only on your Mac. The relay temporarily stores requested content in short-lived job/result queues — job payloads live in Redis-shaped storage with a short TTL and are deleted on delivery.
- The agent token (and your vault path) is stored at
~/.secondbrainbridge-agent.json(mode600); the vault path can also come fromSECONDBRAIN_VAULT. - No secrets are committed; see
.gitignoreand the.env.examplefiles. - The write tool (
create_note) is marked destructive so ChatGPT asks before adding a note.
License
MIT © Isaiah Dupree
Production storage and owner verification
Relay 1.4 uses isolated service-role-only tables/functions on the configured shared Supabase project. Production refuses missing storage configuration, bounds RPC requests to ten seconds, and returns HTTP 503 when storage or signing configuration is unavailable. Apply the checked-in isolated-storage migration before deploying this version; it does not replace another bridge's account tables or functions.
node --env-file=.env.local test/live-storage.mjs verifies the actual persistent store, FIFO, expiry and counters using temporary integration keys. BRIDGE_SESSION_FILE=/private/owner-session.json BRIDGE_READ_TOOL=READ_TOOL node test/live-relay.mjs verifies the actual owner session, PKCE OAuth, hosted MCP and paired-Mac read; choose this bridge's inventory tool. No reviewer data counts as a live acceptance. Credentials and sessions belong outside Git.
Private vault index (source agent 1.1)
Requires Node 22.13+. Set the exact vault in the agent config, then run node agent/cli.mjs index-install. This builds a private SQLite snapshot under ~/Library/Application Support/SecondBrainBridge/ and incrementally checks changes every 15 minutes. It indexes Markdown/text files, excludes dot directories and symlinks, and reports the complete count without a silent 5,000-file cap. Search/list responses include the snapshot time and 15-minute freshness boundary. Fetch reads current file text; creating a note refuses overwrites and invalidates the snapshot. No embedding/model service is started.
node agent/cli.mjs index-status reports counts and freshness. node test/live-index.mjs checks actual ID coverage, private permissions, live text comparisons and read/search results. uninstall removes the refresh job while retaining the private index. No npm publication is claimed for this source upgrade.
来源:README.md,提交 fe4df53
工具
0版本历史
1- v1.3.0最新Sep 16, 2026
评分
已满足适用检查项的 85%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通必需25 分
- 已声明认证方式必需10 分
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
其他 Brain 集成

BrainDog
dog.brain官方发布者
BrainDog 是一个托管记录库,集中保存项目、决策与资金,接入的 AI 代理在开工前读取、结束后写入。

Codebase Brain
由 GitHub 账号 Nomannazir 发布
为本地或公开 git 代码库建立索引,让助手能检索代码、追溯 git 历史、分析改动影响并发现过期文档,结果均带路径与行号引用。

Personal Brain
由 GitHub 账号 zhang-liz 发布
为 AI 助手提供职业人脉记忆,数据以图的形式存放在 FalkorDB 中,可查询联系人、按话题找人并记录你见过的人。

Second Brain
由 GitHub 账号 ara-5 发布
面向AI智能体的共享Graph-RAG记忆:markdown vault、wikilink召回、任务、消息传递。AI 翻译

Make0 Brain
由 GitHub 账号 make0-official 发布
本地离线运行的记忆服务器,让 Claude Code、Cursor、Codex 等 MCP 代理共享一份带版本记录的持久事实库。