Summary
If you're tired of retyping project context every time you open Claude or Cursor, this gives your AI a persistent memory layer. It exposes eight MCP tools for managing "books" and "pages" of context with full text and semantic search via Voyage embeddings. Create books for different projects, insert pages of documentation or preferences, then let your agent search and retrieve exactly what it needs mid-conversation. The backend runs two Go servers: one for OAuth and a web dashboard, another for the MCP protocol itself with bearer token auth. Everything lives in Postgres with pgvector. Useful when you're jumping between projects or working with agents that need to remember your coding standards, API patterns, or domain knowledge without stuffing it all into every prompt.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
8 tools
book_create_or_updateCreate a new Book or update an existing one. All fields (title, source, tags) are required. If book_id is omitted a new book is created and the new book_id is returned. If book_id is provided and exists, its metadata is replaced atomically. If book_id is provided but not found...3 params
Create a new Book or update an existing one. All fields (title, source, tags) are required. If book_id is omitted a new book is created and the new book_id is returned. If book_id is provided and exists, its metadata is replaced atomically. If book_id is provided but not found...
Parameters* required
tagsarrayOptional list of tags to categorize the book (e.g. ['go', 'backend']).
titlestringShort descriptive title of the book. Required.
book_idstringUUID of an existing book to update. Omit to create a new book.
book_getRetrieve all pages of a Book in order by its book_id.1 params
Retrieve all pages of a Book in order by its book_id.
Parameters* required
book_idstringUUID of the book to retrieve.
book_listList available Books. Returns metadata including book_id, title, and tags.2 params
List available Books. Returns metadata including book_id, title, and tags.
Parameters* required
limitintegerMaximum number of books to return. Defaults to 20.
offsetintegerNumber of books to skip for pagination. Defaults to 0.
page_deletePermanently remove a page from a Book using its book_id and page_index. Note: Page indices will not be re-indexed after deletion (gaps are normal).2 params
Permanently remove a page from a Book using its book_id and page_index. Note: Page indices will not be re-indexed after deletion (gaps are normal).
Parameters* required
book_idstringUUID of the book containing the page to delete.
page_indexintegerZero-based index of the page to remove.
page_insertInsert a page of text (≤1000 words) into a Book. Each page is an atomic, semantically meaningful chunk. Maintains retrieval quality via meaningful splitting and overlap.2 params
Insert a page of text (≤1000 words) into a Book. Each page is an atomic, semantically meaningful chunk. Maintains retrieval quality via meaningful splitting and overlap.
Parameters* required
book_idstringUUID of the book to insert the page into.
contentstringPage text content. Max 1000 words; split large content into meaningful chunks.
page_searchPerform semantic search across all Books using a natural language query. Returns matching pages with their book_id and page_index.3 params
Perform semantic search across all Books using a natural language query. Returns matching pages with their book_id and page_index.
Parameters* required
tagsarrayOptional list of tags to filter results by.
limitintegerMaximum number of results to return. Defaults to 5, max 20.
querystringNatural language search query (e.g. 'how to handle retries in Go').
page_updateUpdate a specific page within a Book using its book_id and page_index. Max content size: 1000 words.3 params
Update a specific page within a Book using its book_id and page_index. Max content size: 1000 words.
Parameters* required
book_idstringUUID of the book containing the page to update.
contentstringNew page text content. Max 1000 words.
page_indexintegerZero-based index of the page to replace.
readmeReturns the ContextBook usage guide. Call this once at the start of a session if you have not already loaded the instructions.
Returns the ContextBook usage guide. Call this once at the start of a session if you have not already loaded the instructions.
No parameter schema in public metadata yet.
Stop re-explaining yourself to Agents. Give it the right context, right when needed.
LLMs are stateless — each conversation starts from scratch. ContextBook gives your AI tools a persistent, searchable knowledge library to draw the right context when they need it. No bloatware, no pre-loaded junk. Just the right information, at the right time.
How It Works
flowchart LR
AI["🤖 AI Clients\nClaude · Cursor · Windsurf"]
Browser["🌐 Browser Dashboard"]
MCP["🔌 MCP Server :8081\n8 Bearer-authenticated tools"]
API["⚙️ REST API :8080\nOAuth 2.0 · Books · Pages · Search"]
DB["🗄️ PostgreSQL\npgvector · pg_trgm"]
VOYAGE["🧠 Voyage AI\nvoyage-4 (1024-dim)"]
AI -- "MCP · Bearer Token" --> MCP
Browser -- "Session · HTTP JSON" --> API
MCP --- DB
API --- DB
API -- "OAuth 2.0 PKCE" --> AI
DB --- VOYAGE
Two Go binaries share a PostgreSQL database:
- API server (
cmd/api) — the control plane: user login, OAuth 2.0, dashboard, book/page CRUD - MCP server (
cmd/mcp) — the data plane: 8 MCP tools for AI agents, protected by Bearer tokens
MCP Tools
All tools require a valid Bearer token and are scoped to the authenticated user.
| Tool | Description |
|---|---|
book_create_or_update | Create a Book or update its metadata |
book_list | Paginated list of Book metadata |
book_get | Retrieve all pages of a Book |
page_insert | Push an atomic page into a Book; embeds immediately |
page_update | Replace a page's content; re-embeds |
page_delete | Remove a page (indices not re-numbered) |
page_search | Semantic search across all Books |
readme | Returns the usage guide (call once per session) |
Quick Start
Prerequisites
1. Set up the database
CREATE DATABASE contextbook_db;
\c contextbook_db
CREATE EXTENSION IF NOT EXISTS vector;
CREATE EXTENSION IF NOT EXISTS pg_trgm;
Migrations run automatically on API server startup.
2. Configure environment
cp .env.example backend/.env
# Edit backend/.env — set DATABASE_URL, API_KEY_SALT, VOYAGE_API_KEY
3. Run the backend
cd backend
go run ./cmd/api/main.go # API + dashboard (:8080)
go run ./cmd/mcp/main.go # MCP server (:8081)
4. Run the frontend (optional)
cd frontend
npm install && npm run dev # Vite dev server on :5173
5. Connect an AI client
For Cursor (.cursor/mcp.json):
{
"mcpServers": {
"contextbook": {
"url": "http://localhost:8081/mcp"
}
}
}
For any MCP-compatible client, point the server URL to http://localhost:8081/mcp.
Documentation
- Backend README — API routes, auth flows, database schema, MCP tools, configuration
- Frontend README — components, routing, design system, development setup
- Architecture — full system overview with Mermaid diagrams
Project Structure
context-book/
├── backend/
│ ├── cmd/api/main.go REST API + auth server
│ ├── cmd/mcp/main.go MCP tool server
│ └── internal/
│ ├── api/ REST handlers + routes
│ ├── auth/ OAuth 2.0 PKCE, sessions, SSO
│ ├── context/ Book/Page business logic
│ ├── db/ pgx queries + migrations
│ ├── embedding/ Voyage AI client
│ ├── logger/ slog + HTTP access logging
│ └── mcp/ 8 MCP tool handlers
├── frontend/ React 19 + Vite + TypeScript SPA
│ └── src/
│ ├── App.tsx Router + app shell
│ ├── lib/api.ts HTTP client
│ └── components/ UI components
├── Dockerfile API server container
├── Dockerfile.mcp MCP server container
└── go.work Go workspace
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/my-feature) - Make your changes
- Ensure the backend compiles (
cd backend && go build ./cmd/api ./cmd/mcp) - Ensure the frontend builds (
cd frontend && npm run build) - Commit and push
- Open a Pull Request
License
MIT — see the LICENSE file for details.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →