Repository Intelligence Engine
Enables querying a TypeScript repository's structure (symbols, imports/exports, references) through direct queries, avoiding repetitive grep operations.
README
Repository Intelligence Engine
A TypeScript repository indexing engine that builds a structural model of a codebase — symbols, imports/exports, and references — and answers precise navigation questions about it directly, instead of re-discovering structure by grepping every session.
The problem
AI coding agents start every session with zero structural memory of a repo. Answering "how does login work?" means an iterative grep → open → grep → open cycle, repeated from scratch each time. This engine replaces that with direct queries against a pre-built index.
What it does
The engine parses a TypeScript repo with the TypeScript Compiler API and stores a structural model in SQLite. Five queries run over that index:
| Query | Answers |
|---|---|
find_module(name) |
Which file(s) define this symbol? |
find_related_files(file) |
What does this file import, and what imports it? |
find_symbol_references(symbol) |
Everywhere this symbol is used |
dependency_path(a, b) |
Is there an import path between two symbols, and what is it? |
reindex(path?) |
Rebuild the index |
The engine/ functions are callable directly (CLI, tests) — the engine is the product. It also supports Claude Code and any other MCP-compatible client through an integrated MCP server.
Status
Early scaffold. Core is being built in the order in the project plan:
indexer → storage + basic queries → references → dependency_path/reindex → MCP server → benchmark harness → docs.
Benchmark
Before/after table lands here once the harness (step 6) runs against a real repo — median file-reads and tool-calls per task, baseline vs. MCP-assisted.
Development
npm install
npm run build # tsc -> dist/
npm run index -- ./tsconfig.json repo-index.db # index a repo
npm run mcp # start the MCP server (stdio)
npm test # vitest
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.