Context Book

aditya201551/context-book

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.

GitHub stars: 6
tools: 8
transport: HTTP
last updated: May 17, 2026

View on GitHub

Tools

8 tools

Public tool metadata for what this MCP can expose to an agent.

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

book_idstring

UUID of an existing book to update. Omit to create a new book.

tagsarray

Optional list of tags to categorize the book (e.g. ['go', 'backend']).

titlestring

Short descriptive title of the book. Required.

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_idstring

UUID 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

limitinteger

Maximum number of books to return. Defaults to 20.

offsetinteger

Number 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_idstring

UUID of the book containing the page to delete.

page_indexinteger

Zero-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_idstring

UUID of the book to insert the page into.

contentstring

Page 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

limitinteger

Maximum number of results to return. Defaults to 5, max 20.

querystring

Natural language search query (e.g. 'how to handle retries in Go').

tagsarray

Optional list of tags to filter results by.

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_idstring

UUID of the book containing the page to update.

contentstring

New page text content. Max 1000 words.

page_indexinteger

Zero-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.

Readme

ContextBook

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

View the full README on GitHub

Details

Repository: github.com/aditya201551/context-book
Website: context-book-production.up.railway.app
Transport: HTTP
Registry: MCP registry, active