semihkayan/codeweave-mcp
MCP server that gives AI agents deep code understanding. Builds AST, call graphs, type graphs, and hybrid semantic search — so your agent queries structured indexes instead of dumping files into context. 7 languages. Zero config. One command setup.
Platform-specific configuration:
{
"mcpServers": {
"codeweave-mcp": {
"command": "npx",
"args": [
"-y",
"codeweave-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> <h1 align="center">@codeweave/mcp</h1> <p align="center"> <strong>Give your AI agent structured code understanding — not just file dumps.</strong> </p> <p align="center"> <a href="https://www.npmjs.com/package/@codeweave/mcp"></a> <a href="https://github.com/semihkayan/codeweave-mcp/blob/main/LICENSE"></a> </p> </p>
---
CodeWeave is an MCP server that gives AI agents cheap, precise code intelligence. Instead of dumping entire files into context, your agent queries local indexes — AST, call graph, type graph, hybrid semantic search — and gets back only what it needs.
Less tokens. More relevant context. Better decisions.
The semantic search pipeline is the heart of the system: a 6-stage hybrid engine combining vector embeddings, full-text search, and structural density scoring. Tested extensively across large production codebases — Java monoliths, TypeScript monorepos, Python ML pipelines, Go microservices — with consistently strong retrieval accuracy.
> Actively developed. New tools and improvements ship regularly. Contributions and feedback are welcome.
cd your-project
npx @codeweave/mcpThat's it. The setup wizard handles everything:
@codeweave/mcp globally> Note: The first run requires a one-time download of Ollama and the embedding model. This takes a few minutes but only happens once.
Op
Loading reviews...