Vector DB Comparison

Run the same corpus and queries across three vector DBs and let the numbers decide.

This is one of FrootAI's cross-server composition recipes — a single solution play whose agent attaches Qdrant + ChromaDB + Pinecone and runs them as one pipeline. Qdrant, ChromaDB, and Pinecone each answer the same workload behind one agent, so you get an apples-to-apples recall, latency, and cost bake-off instead of a vendor pitch.

What you'll build

The agent's task, in one line:

Run the same embedding workload across Qdrant, ChromaDB, and Pinecone and produce a recall, latency, and cost comparison.

It attaches qdrant, chromadb, pinecone 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 (~$18.00 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.