RAG from a GitHub Repo

Point an agent at a GitHub repo and get a queryable RAG index in one run.

This is one of FrootAI's cross-server composition recipes — a single solution play whose agent attaches GitHub + Markitdown + Azure AI Search and runs them as one pipeline. GitHub fetches the repo, Markitdown normalizes the docs to clean Markdown, and Azure AI Search builds the vector index. Three servers, one pipeline — repo in, grounded answers out.

What you'll build

The agent's task, in one line:

Index a GitHub repo: convert its docs to Markdown and build a RAG index in Azure AI Search.

It attaches github, markitdown, azure via the play's mcp_scope, runs the loop end to end, and detaches when it's done.

Why compose instead of chain

Federating MCP servers behind one agent means the model decides which tool to call when — no brittle glue code wiring outputs to inputs. The attach list is declarative; the engine wires the servers before the first turn and tears them down after. You get the composition without owning the plumbing.

Run it

The recipe ships a runnable, offline harness plus the full mcp_scope.attached snippet, a cost breakdown (~$22.00 per 100 runs), and a security note for every credential. Read the full recipe:

- 📖 Cookbook recipe - ▶️ Open in Studio

The takeaway

The interesting MCP work isn't any single server — it's the federation. This recipe is one worked example of many in the FrootAI cookbook. Compose, don't chain.