Booklib
Detects what your AI doesn't know about your project and fixes it. Post-training gap detection, runtime context injection via MCP.
What is Booklib?
Booklib is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to detects what your ai doesn't know about your project and fixes it. post-training gap detection, runtime context injection via mcp.
Detects what your AI doesn't know about your project and fixes it. Post-training gap detection, runtime context injection via MCP.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Detects what your AI doesn't know about your project and fix
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx booklibConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Booklib
Booklib is a context engineering tool for AI coding assistants that detects post-training knowledge gaps in your project dependencies and automatically injects the missing context at runtime via MCP. It scans packages across 10 ecosystems (npm, PyPI, Maven, Crates.io, Go modules, and more), identifies APIs published after the AI model's training cutoff, and fetches current documentation from Context7 and GitHub to fill those gaps before the AI writes code. Teams also use it to capture internal decisions — like 'use PaymentIntents not Charges' — and inject them as the AI generates code, preventing both hallucinated APIs and code that violates project conventions.
Prerequisites
- Node.js 18 or later installed
- An MCP-compatible AI coding tool (Claude Code, Cursor, Copilot, Windsurf, Gemini CLI, etc.)
- npm (comes with Node.js) to install the booklib CLI globally
- Optional: Ollama for local embedding mode, or a cloud AI provider for cloud processing mode
Install the booklib CLI globally
Install the @booklib/core package from npm. This gives you the booklib command used for all setup and daily operations.
npm install -g @booklib/coreRun the guided initialization wizard
The init command detects your project stack, automatically configures MCP for your AI tools, and builds the initial knowledge index. Answer the prompts to choose your processing mode (fast BM25, local Ollama, or cloud AI).
booklib initAnalyze your project for post-training gaps
Run analyze to see which dependencies were published after your AI model's training cutoff and which files/APIs in your codebase are affected.
booklib analyzeAuto-resolve the detected gaps
The resolve-gaps command fetches current documentation for each affected library from Context7 and GitHub, injecting it into the knowledge index so your AI has accurate API information.
booklib resolve-gapsCapture team-specific decisions
Store architectural decisions and coding conventions that don't exist in any public documentation. These are checked at runtime as the AI writes code.
booklib capture --title "use PaymentIntents not Charges" --type decisionRun a health check
Verify that all skills and the MCP configuration are working correctly before using your AI tools.
booklib doctorBooklib Examples
Client configuration
Booklib's init command generates this configuration automatically. If manual setup is needed, add it to your MCP client config (path may vary by tool).
{
"mcpServers": {
"booklib": {
"command": "npx",
"args": ["booklib"]
}
}
}Prompts to try
Once booklib is running as an MCP server your AI tools will automatically receive context injections. These are typical requests that benefit most from booklib's gap detection.
- "Write an API route using the AI SDK v6 streamText function"
- "Show me which dependencies in this project have post-training knowledge gaps"
- "Check if this file uses any APIs that violate our team decisions"
- "Connect my Notion database to booklib so team docs are included in context"Troubleshooting Booklib
booklib init does not detect my AI tool or configure MCP automatically
Run 'booklib doctor' to see what was detected. You can also manually add the MCP config block to your tool's config file and then run 'booklib index' to build the index independently.
resolve-gaps fails for some packages with 'documentation not found'
For packages not covered by Context7 or GitHub, use 'booklib connect <path>' to index local documentation or web docs manually. Run 'booklib sources' to see what is currently connected.
AI still generates incorrect API calls after running resolve-gaps
Run 'booklib check-imports <file>' on the affected file to verify the import is flagged as unknown. If the gap persists, rebuild the index with 'booklib index' and confirm the package appears in 'booklib gaps' output.
Frequently Asked Questions about Booklib
What is Booklib?
Booklib is a Model Context Protocol (MCP) server that detects what your ai doesn't know about your project and fixes it. post-training gap detection, runtime context injection via mcp. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Booklib?
Follow the installation instructions on the Booklib GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Booklib?
Booklib works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Booklib free to use?
Yes, Booklib is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Booklib Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Booklib? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Booklib in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Booklib?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.