Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@rag-legacy show me how token refresh is implemented"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local RAG system for semantic recall of the vite-mf-monorepo legacy codebase from Claude Code.
Allow Claude Code, when working in the Next.js project, to find legacy code and patterns by meaning — not by filename. Instead of searching by file name or regex, Claude Code calls recall("how was token refresh handled?") and gets back the most semantically relevant chunks from the legacy codebase.
Related MCP server: RAGex
1. INDEXING (one-time, then re-run when legacy changes)
pnpm index
→ walks vite-mf-monorepo (349 files)
→ chunks each file into overlapping segments
→ embeds each chunk via nomic-embed-text (Ollama, local)
→ stores chunks + embeddings in MongoDB Atlas (legacy_chunks)
2. RECALL (at query time, triggered by Claude Code)
Claude Code calls the recall() MCP tool with a natural language query
→ query is embedded via nomic-embed-text
→ vector search in MongoDB Atlas finds the top N most similar chunks
→ Claude Code receives file paths + content ranked by semantic similarityComponent | Choice |
Embeddings | nomic-embed-text via Ollama (local, 768 dimensions) |
Vector store | MongoDB Atlas M0 — |
Vector index | Atlas Vector Search — cosine similarity, filters on |
MCP server | Local stdio server exposing |
Language | TypeScript |
Ollama must be running locally — it handles all embedding generation.
Download and install from ollama.com
Pull the embedding model:
ollama pull nomic-embed-textVerify:
ollama listOllama must be running in the background before indexing or using recall.
src/
indexer/
index.ts # indexing pipeline entry point
walk.ts # recursive file walker with ignore rules
classify.ts # classifies files as app or package
chunk.ts # splits large files into overlapping chunks
retriever/
recall.ts # embeds query + runs Atlas vector search
mcp/
server.ts # stdio MCP server exposing recall() to Claude CodeLegacy (vite-mf-monorepo) — indexed in MongoDB Atlas
Next (nextjs-multizone-tmdb) — read live by Claude Code, not indexed
Indexed: .ts, .tsx, .md — source files and config files
Ignored: node_modules, dist, __mf__temp, .netlify, scripts/, *.test.ts, *.spec.ts, *.d.ts, *.css, *.json, *.sh, .env*, vitest.config.ts, vitest.setup.ts
pnpm install
cp .env.example .env # fill in MONGODB_URI and LEGACY_PATHVariable | Description |
| MongoDB Atlas connection string |
| Absolute path to the |
The MCP server must be registered in the Next.js project so Claude Code can call recall().
Create .mcp.json at the root of nextjs-multizone-tmdb:
{
"mcpServers": {
"rag-legacy": {
"type": "stdio",
"command": "pnpm",
"args": ["--prefix", "/absolute/path/to/vite-mf-monorepo-rag", "run", "mcp"],
"env": {
"MONGODB_URI": "your_mongodb_uri",
"LEGACY_PATH": "/absolute/path/to/vite-mf-monorepo"
}
}
}
}Then in Claude Code, run /mcp and accept the server when prompted.
pnpm index # run the full legacy indexing pipeline
pnpm mcp # start the MCP server (Claude Code does this automatically)
pnpm build # compile TypeScript
pnpm lint # ESLint
pnpm type-check # type check without compilationRun pnpm index whenever the legacy codebase changes. The pipeline clears legacy_chunks and re-indexes everything from scratch.
This server cannot be deployed
Project memory, semantic code search, and grounded agent context.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
