CLI-first semantic code search with MCP integration, powered by LanceDB and AST parsing.
mcp-vector-search is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view bobmatnyc/mcp-vector-search --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 112 days ago.
47 GitHub stars indicate community interest.
20 open issues signal maintenance load.
NOASSERTION license detected.
0 security/trust notes recorded.
Setup difficulty is 2/5.
Connect any AI model to 1200+ integrations (MCP, CLI, API)
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
Official Microsoft Learn MCP server and CLI tool providing real-time, trusted Microsoft docs and code samples to AI agents.
Open-source credential gateway with a built-in vault. give your AI agents access to services without exposing keys.
This tool helps developers find code by meaning, not just keywords. It understands code structure and supports 13 languages. It works as a command-line tool and can integrate with AI assistants via MCP.
MCP Vector Search is a modern, fast, and intelligent code search tool that understands your codebase through semantic analysis and AST parsing. It uses LanceDB as the default vector database for serverless, file-based storage. Key features include semantic search, AST-aware parsing for 13 languages, a knowledge graph with KuzuDB, interactive D3.js visualizations, development narratives from git history, real-time indexing, and zero-configuration setup. It offers 17 MCP tools for AI assistant integration, chat mode with LLM-powered Q&A, and CodeT5+ embeddings. Performance optimizations include sub-second search, IVF-PQ vector index for 4.9x faster queries, and Apple Silicon M4 Max support. The tool is production-ready with write buffering, auto-indexing, and comprehensive error handling.
47
Stars
11
Forks
20
Issues
NOASSERTION
License
CLI-first semantic code search with MCP integration, powered by LanceDB and AST parsing.
Software developers working on large codebases who need fast, semantic code search., AI/ML engineers integrating code search into AI assistants via MCP., DevOps engineers and technical leads who need code analysis and documentation tools.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Review repository permissions, executed commands, data sent to external services, and dependencies before use.
Similar or complementary options to evaluate include metorial, mcp-context-forge, Microsoft Learn MCP Server.
Aug 20, 2026