MCP use case
MCP server for coding agents.
Tools in the editor, or a CLI.
The use case
Cursor and Claude Code.
Tools in the editor, or a CLI.
The same Flow project can also ship to WhatsApp, iMessage, Telegram.
What Flow handles
The product work, not the plumbing.
- The same typed tools are served as an MCP server and a CLI. No transport, schema or protocol code.
- Flow handles each user’s sign-in, so the assistant only reaches what that person can.
- Simulated users check which prompts should and should not call your tools, and every call is traced.
How to begin
A real route to launch.
- 01
Create a Flow project
Run npx @flow-engineer/flow new my-agent, or ask Claude Code or Codex to set it up. You get one folder: the agent’s instructions, its tools, its skills and its tests.
- 02
Write what it can do as tools
Each job is a TypeScript function with a typed input that calls your API: check an order, book a slot, find a deal. No protocol code.
- 03
Test it on simulated users
Run npx @flow-engineer/flow test. Simulated users try the scenarios that matter, including people who change their mind or ask for something your agent should refuse.
One project, more surfaces
Build this on MCP.
Start with the product page, then ship the same agent and tools wherever your customers use them.