Skip to content

Conversation

alinaqi
Copy link

@alinaqi alinaqi commented Sep 26, 2025

Summary

Adds the Source to Knowledge Base (src-to-kb) MCP server to the community servers list.

Description

src-to-kb is an MCP server that converts source code repositories into searchable knowledge bases with:

  • AI-powered search using OpenAI GPT-5
  • Intelligent code chunking with configurable overlap
  • OpenAI embeddings for semantic search
  • Support for 20+ programming languages
  • MCP tools for generating, searching, and managing knowledge bases

Links

Checklist

  • Added to correct alphabetical position in Community Servers section
  • Follows existing format and style
  • Repository is public and accessible
  • MCP server is functional and documented

Adds src-to-kb to the community servers list. This MCP server converts source code repositories into searchable knowledge bases with AI-powered search capabilities.
- **[Solver](https://github.com/szeider/mcp-solver)** - Solves constraint satisfaction and optimization problems .
- **[Solvitor](https://github.com/Adeptus-Innovatio/solvitor-mcp)** – Solvitor MCP server provides tools to access reverse engineering tools that help developers extract IDL files from closed - source Solana smart contracts and decompile them.
- **[Sourcerer](https://github.com/st3v3nmw/sourcerer-mcp)** - MCP for semantic code search & navigation that reduces token waste.
- **[Source to Knowledge Base](https://github.com/vezlo/src-to-kb)** - Convert source code repositories into searchable knowledge bases with AI-powered search using GPT-5, intelligent chunking, and OpenAI embeddings for semantic code understanding.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi, is this actually an MCP server, or more like a CLI tool? Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants