PDF to Research Deck

Convert a dense PDF into a grounded, cited research summary.

This is one of FrootAI's cross-server composition recipes — a single solution play whose agent attaches Markitdown + Context7 + Tavily and runs them as one pipeline. Markitdown extracts the PDF to Markdown, Context7 grounds the technical claims, and Tavily fills the gaps with current sources — so the deck is accurate, not approximate.

What you'll build

The agent's task, in one line:

Convert the source PDF to Markdown, enrich it with Context7 docs and Tavily search, and assemble a research deck.

It attaches markitdown, context7, tavily-ai 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 (~$5.40 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.