codesearch
★ 93
vs
vector_mcp
★ 13
codesearch vs vector_mcp
codesearch: codesearch is a token-efficient MCP server for AI agents that enables local semantic code search. It integrates with OpenCode, Claude Code and other AI assistants to perform intelligent code searches with minimal token usage, all running locally with no external API calls.; vector_mcp: VectorMCP is a Ruby framework implementing the MCP server specification. It provides class-based tools, resources, prompts, and supports streamable HTTP transport with authentication, authorization, and middleware.
01
TL;DR
codesearchRAG / Knowledge Base · ★ 93
AI-assisted code understanding through natural language queries
vector_mcpRAG / Knowledge Base · ★ 13
Build MCP-compatible servers for AI tools and assistants
02
Side-by-Side Comparison
Field
codesearchvector_mcpCategory
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 93
★ 13
License
Apache-2.0
MIT
Install Command
git clone https://github.com/flupkede/codesearch.git && cd codesearch && cargo build --release && sudo cp target/release/codesearch /usr/local/bin/
gem install vector_mcp
Updated
1d ago
6d ago
Open Source
Yes
Yes
Tags
claude-code, code-search, embeddings
mcp, mcp-sdk, mcp-server
03
Features
codesearch01Token-efficient AI integration with compact responses
02Semantic, hybrid, and neural reranking search modes
03Incremental indexing with three-layer embedding cache
04Git-aware automatic index placement and branch detection
05Privacy-first local processing with no external calls
vector_mcp01Streamable HTTP transport with session management and MCP 2025-11-25 compliance
02Class-based tools via VectorMCP::Tool DSL and block-based register_tool API
03Rack and Rails mounting through server.rack_app
04Opt-in authentication and authorization with middleware hooks
05Image-aware tools/resources/prompts, roots, and server-initiated sampling
04
Use Cases
codesearch↳AI-assisted code understanding through natural language queries
↳Codebase navigation and reference discovery
↳Integration with AI coding assistants like OpenCode and Claude Code
vector_mcp↳Build MCP-compatible servers for AI tools and assistants
↳Integrate MCP endpoints into Ruby on Rails applications
↳Expose custom tools, resources, and prompts via MCP protocol
FAQ
FAQ
What is the difference between codesearch and vector_mcp?
Both codesearch and vector_mcp are in the RAG / Knowledge Base category. codesearch has 93 stars, while vector_mcp has 13 stars.
Which is better, codesearch or vector_mcp?
The best choice depends on your use case. Choose codesearch if AI-assisted code understanding through natural language queries, and vector_mcp if Build MCP-compatible servers for AI tools and assistants.
Is codesearch free or open source?
Yes, codesearch is open source on GitHub (Apache-2.0).
Is vector_mcp free or open source?
Yes, vector_mcp is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→