API Test MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 31 Aug 2026.
Call the real API and check the response against your OpenAPI spec.
Today is the operative word: we check API Test MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add api-test-mcp -- npx -y api-test-mcp
{
"mcpServers": {
"api-test-mcp": {
"args": [
"-y",
"api-test-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.api-test-mcp]
command = "npx"
args = ["-y", "api-test-mcp"]
{
"mcpServers": {
"api-test-mcp": {
"args": [
"-y",
"api-test-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"api-test-mcp": {
"args": [
"-y",
"api-test-mcp"
],
"command": "npx"
}
}
}
Design, mock, test, document and monitor your APIs from one living OpenAPI spec.
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
A real Mac for your agent: build, test, run, and tap through iOS apps on the simulator.
QA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.
Turn an OpenAPI spec into WireMock stubs, contract tests and chaos scenarios, on local LLMs.
Crash-test your AI agent on real professional decisions, graded against what actually happened.
Run, write and test the API requests saved in a Kurlo workspace, the open source API client.
Deterministic pool and spa water test log. Checks readings against US CDC ranges. No AI.
Answers built from our own checks of this server.