Example Prompts

Once the MCP server is installed, you work with Thunder Client by chatting with your AI assistant. Describe the outcome you want, and the assistant uses the available tools to achieve it.

The prompts below cover common API development workflows. Adapt the collection names, URLs, and file paths to your project.

Before You Start

Confirm the connection. Make sure the MCP server is connected. See the Verify step for your AI tool on the Installation page.
Specify your project if needed. The assistant usually works in your current project. If it can’t determine which project to use, include the absolute path to your project (for example, /Users/john/shop-api) in your prompt.
Use variables for secrets. Reference values as {{varName}}. The assistant can see variable names but not their values, so set values in Thunder Client → Environments.

Explore Your Workspace

Summarize Collections and Environments


Check that Thunder Client is set up for this project, then summarize my
collections and environments, and tell me which environment is active.

Build Collections

Generate a Collection from Source Code


Analyze the Express routes in src/routes/ and create a "Shop API" collection
with one folder per resource. Set the base URL to http://localhost:3000, use
path-only request URLs, and include a realistic sample body for each POST and
PUT request.

Import Endpoints from an OpenAPI Spec


Read openapi.yaml and create a "Payments API" collection that covers every
endpoint, grouped into folders by tag. Set the base URL to the spec's server
URL, use path-only request URLs, and add each operation's summary as the
request docs.

Configure OAuth 2.0 Client Credentials


Configure the "Billing API" collection to use OAuth 2.0 client credentials with
the token URL https://auth.example.com/oauth/token, {{clientId}} and
{{clientSecret}}, and the scope "billing:read billing:write".

Test Your APIs

Add Baseline Tests


Add tests to every request in the "Orders" folder of the "Shop API" collection:
the expected success status code, response time under 1000 ms, and a JSON body
that contains an "id" field.

Chain Requests in an End-to-End Flow


In the "Orders" folder, create an end-to-end flow: create an order, save the
returned id to {{orderId}}, fetch the order by {{orderId}}, update its status
to "shipped", then delete it. Add tests to each step that verify the response.

Validate Response Structure


Add tests to GET /products in the "Shop API" collection that verify the
response is an array, each item has a numeric "id" and a string "name", and
the "X-Request-Id" response header is present.

Run and Debug

Run a Smoke Test against Staging


Run the "Shop API" collection using the "Staging" environment and give me a
summary of the results, grouped by folder, with any failed tests listed first.

Investigate and Fix Failures


Run the "Shop API" collection. For each failing test, show me the request and
the failed assertion, identify the most likely cause, and propose a fix before
making any changes.

Diagnose an Authorization Error


GET /orders/{id} in the "Shop API" collection returns 401. Compare its auth and
headers with a request in the same collection that succeeds, explain the
difference, and fix it.

Configure Collection Run Options


Configure the "Shop API" collection to run 3 iterations with a 500 ms delay
between requests and stop on the first failure. Then run it and report the
results.

Maintain Collections

Replace Hard-Coded Values with Variables


Review all requests in the "Shop API" collection for hard-coded hosts, API
keys, or IDs in URLs and headers. Replace them with environment variables and
list the variables I need to add to my environment.

Document a Collection


Add docs to each request in the "Shop API" collection describing its purpose,
required parameters, and an example response, based on the route handlers in
src/routes/.

Clean Up Obsolete Requests


List the requests in the "Legacy" folder of the "Shop API" collection. Show me
the details of "Old checkout" and wait for my confirmation before deleting it.

Tips

Describe the outcome, not the tool. For example, “Check my setup” works better than naming a specific tool.
Use exact names. Refer to collections and folders exactly as they appear in Thunder Client.
Ask for a plan first. For large changes, ask the assistant to describe what it will create or modify before it starts.
Start with a setup check. If something isn’t working, ask the assistant to check your setup. It shows the project directory and data path the CLI is using.
Review deletions before approving them. Deleted requests can’t be recovered.
Review the results in Thunder Client. Everything the assistant creates appears in the sidebar, ready for you to edit.