Author

Powerduck

2 min read

We gave a partner’s AI agent 12 of our 47 endpoints. Here is how.

A concrete Cloud walkthrough: publish a managed Streamable HTTP MCP endpoint from one spec, expose twelve operations out of forty-seven, gate agents with a rotated bearer key, inject upstream auth, and pin the partner to an immutable version.

Read article
4 min read

Stop pasting API docs into AI coding agents: serve the spec over MCP

Pasted docs rot mid-session, burn tokens on every conversation, and leave the agent guessing field names. An MCP server generated from the OpenAPI spec gives an agent callable tools with typed inputs instead of prose. Here is when that wins and when it does not.

Read article
2 min read

Your API already describes the tools your AI agent needs

Hand-writing tool wrappers around existing order and inventory endpoints means maintaining every contract twice. Generate the MCP server from the OpenAPI spec, start with read-only tools, and widen the surface deliberately.

Read article
4 min read

API contract testing without Pact's overhead: a lighter workflow for small teams

Consumer-driven contracts with Pact are powerful but bring a broker, pactfiles, and a workflow small teams never maintain. Here is what contract testing is really protecting, and a lighter OpenAPI-based setup that catches the same integration bugs with tools you already run.

Read article
2 min read

A 200 is not done: make the AI walk the business scenario

The create call returned 200, the detail view 404s, and cancel accepts an illegal state. Scenario tests chain real calls, pass data between steps, and hand the agent evidence to fix with.

Read article
4 min read

Scenario testing for REST APIs: writing user-journey tests from OpenAPI

A folder of requests that each return 200 is not a test suite. A scenario chains requests the way a user walks the product: create, capture, poll, act, assert. Here is how to derive scenarios from an OpenAPI spec and run them against mock then staging.

Read article