Src to KB

v1.0.0โ€ขDeveloper Toolsโ€ขstable

๐Ÿ“‡ ๐Ÿ  โ˜๏ธ - Convert source code repositories into searchable knowledge bases with AI-powered search using GPT-5, intelligent chunking, and OpenAI embeddings for semantic code understanding.

cli-toolcode-analysiscode-indexingcode-searchdeveloper-tools
Share:
32
Stars
0
Downloads
0
Weekly
0/5

What is Src to KB?

Src to KB is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐Ÿ“‡ ๐Ÿ  โ˜๏ธ - convert source code repositories into searchable knowledge bases with ai-powered search using gpt-5, intelligent chunking, and openai embeddings for semantic code understanding.

๐Ÿ“‡ ๐Ÿ  โ˜๏ธ - Convert source code repositories into searchable knowledge bases with AI-powered search using GPT-5, intelligent chunking, and OpenAI embeddings for semantic code understanding.

This server falls under the Developer Tools and Knowledge & Memory categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • ๐Ÿ“‡ ๐Ÿ  โ˜๏ธ - Convert source code repositories into searchable kn

Use Cases

Convert source code repositories into searchable knowledge bases with AI.
Enable semantic code search using intelligent chunking and embeddings.
Understand large codebases through AI-powered code indexing and analysis.
vezlo

Maintainer

LicenseNOASSERTION
Languagejavascript
Versionv1.0.0
UpdatedMay 3, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx src-to-kb

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Src to KB

Src-to-KB converts source code repositories and Notion pages into searchable, AI-queryable knowledge bases using OpenAI embeddings and intelligent chunking. It exposes an MCP server that lets Claude and other AI clients search and reason over large codebases without loading every file into context. Developers use it to ask high-level architectural questions, find implementation patterns, and understand unfamiliar codebases through natural language queries backed by semantic vector search.

Prerequisites

  • Node.js 18 or higher and npm installed
  • An OpenAI API key (required for embeddings and AI-powered search with GPT models)
  • The source code repository you want to index, available on disk
  • An MCP-compatible client such as Claude Desktop or Claude Code
  • Optional: a Notion integration token if indexing Notion pages instead of code
1

Install the src-to-kb package

Install globally via npm so that all CLI commands (src-to-kb, src-to-kb-search, src-to-kb-mcp) are available on your PATH.

npm install -g @vezlo/src-to-kb
2

Set your OpenAI API key

Export the OPENAI_API_KEY environment variable before running any command that generates embeddings or performs AI-powered searches.

export OPENAI_API_KEY=sk-your-openai-key-here
3

Generate the knowledge base from your repository

Run src-to-kb against your project directory. The --with-embeddings flag generates vector embeddings for semantic search. The output defaults to ./knowledge-base.

src-to-kb ./my-project --output ./kb --with-embeddings
4

Test the knowledge base with a search query

Verify the index is working correctly by running a semantic search against it. The developer mode returns code-level answers.

src-to-kb-search search "how is authentication handled" --kb ./kb --mode developer
5

Start the MCP server

Launch the MCP server pointing at your generated knowledge base so Claude and other MCP clients can query it.

src-to-kb-mcp --kb ./kb
6

Add to your MCP client configuration

Register the MCP server in Claude Desktop or Claude Code so it is available as a tool during conversations.

# For Claude Code:
claude mcp add src-to-kb -- node /path/to/mcp-server.mjs

# Or use the auto-installer:
src-to-kb-mcp-install

Src to KB Examples

Client configuration

Claude Desktop configuration for the src-to-kb MCP server with OpenAI API key injected as an environment variable.

{
  "mcpServers": {
    "src-to-kb": {
      "command": "npx",
      "args": ["@vezlo/src-to-kb"],
      "env": {
        "OPENAI_API_KEY": "sk-your-openai-key-here"
      }
    }
  }
}

Prompts to try

Example prompts to query your indexed codebase through the MCP server.

- "How does this codebase handle user authentication and session management?"
- "Find all places where database connections are opened and explain the connection pooling strategy."
- "What design patterns are used in the payment processing module?"
- "Show me how errors are propagated from the service layer to the API layer."

Troubleshooting Src to KB

Search returns no results or generic keyword matches instead of semantic results

Ensure you passed --with-embeddings when running src-to-kb and that OPENAI_API_KEY is set. Without embeddings the tool falls back to keyword pattern matching, which is less accurate.

src-to-kb command not found after installation

Check that npm's global bin directory is on your PATH. Run 'npm bin -g' to find the directory and add it to PATH in your shell profile (e.g., ~/.zshrc or ~/.bashrc).

Indexing fails on large files or runs out of memory

Use --max-file-size to cap file sizes (default 10 MB) and --exclude to skip build output directories like node_modules, dist, or .git. For very large repos, index subdirectories separately.

Frequently Asked Questions about Src to KB

What is Src to KB?

Src to KB is a Model Context Protocol (MCP) server that ๐Ÿ“‡ ๐Ÿ  โ˜๏ธ - convert source code repositories into searchable knowledge bases with ai-powered search using gpt-5, intelligent chunking, and openai embeddings for semantic code understanding. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Src to KB?

Follow the installation instructions on the Src to KB GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Src to KB?

Src to KB works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Src to KB free to use?

Yes, Src to KB is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "src-to-kb": { "command": "npx", "args": ["-y", "src-to-kb"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use Src to KB?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides