vezlo/src-to-kb
by Various
Convert source code to LLM ready knowledge base
MCP
vezlo/src-to-kb
Added 1 June 2026
Overview
This JavaScript tool converts source code directories into a structured knowledge base format optimized for large language models. It parses files and outputs a text-based representation that preserves code context and relationships.
Best for
Best for
Developers who need a quick, no-fuss way to package source code for LLM-based code review or documentation tasks
Use cases
- Preparing codebases for LLM-based code analysis or documentation generation
- Creating context snippets for AI assistants to understand a project's structure
- Bundling source code into a single file for use with LLM prompts
How to use
Install
npm install -g @vezlo/src-to-kb Tools exposed
npxnode
Tested with
Claude Code, Cursor
Notes
This JavaScript tool converts source code directories into a structured knowledge base format optimized for large language models. It parses files and outputs a text-based representation that preserves code context and relationships.
33 stars on GitHub. Last updated 2025-12-30.
Use cases
- Preparing codebases for LLM-based code analysis or documentation generation
- Creating context snippets for AI assistants to understand a project’s structure
- Bundling source code into a single file for use with LLM prompts
Pros
- Lightweight and simple to use with npm or as a CLI
- Outputs a single file easy to feed into LLM context windows
- Written in JavaScript, widely accessible to web developers
Cons
- Low star count may indicate limited community or ongoing maintenance
- Output format fixed, may not suit all LLM ingestion workflows
- No built-in filtering or exclusion of irrelevant files beyond basic ignore patterns
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Lightweight and simple to use with npm or as a CLI
- Outputs a single file easy to feed into LLM context windows
- Written in JavaScript, widely accessible to web developers
Cons
- Low star count may indicate limited community or ongoing maintenance
- Output format fixed, may not suit all LLM ingestion workflows
- No built-in filtering or exclusion of irrelevant files beyond basic ignore patterns
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.