专为 Cursor 设计的轻量 API 接口测试 MCP Server

The most complete MCP server for API testing. 27 tools: requests, assertions, flows, OpenAPI, mock data, load testing, collections, environments, cURL export, response diffing. Zero config, zero dependencies.

MCP server for HTTP API testing with Playwright. Supports full CRUD operations, path/query parameters, and comprehensive error handling for API automation workflows.

The most complete MCP server for API testing. 42 tools: HTTP requests (with token-optimized responses), assertions, request flows, OpenAPI import, mock data, load testing, collections, environments, native export/import, Postman import/export, cURL export

MCP server that calls your real API and checks the response against your OpenAPI spec — contract testing, auth presets, spec diffing, and health checks for Claude Code, Cursor, and Windsurf.

MCP server that lets AI agents load an OpenAPI spec, call real endpoints, validate responses against the documented schema, run a full contract-test pass, diff two spec versions for breaking changes, and health-check a set of endpoints.

Enable seamless file operations, repository management, and advanced search functionalities on GitHub. Automate your workflow with automatic branch creation and comprehensive error handling, ensuring your Git history is preserved. Enhance your development experience by integrating GitHub capabilities directly into your applications.

Disposable email inboxes via API + MCP server for testing

API testing and documentation tools for Claude Code — test endpoints, parse OpenAPI specs, generate clients and tests

Model your API as a graph once. Long-chain integration tests, layer × environment matrices, CI-ready runs, and an MCP server — all from the same YAML.

MCP Server for comprehensive AI-powered API testing from OpenAPI specifications

OpenAPI testing and deterministic API fuzzing for AI agents—catch contract bugs before unsafe calls with local-first sealed plans, MCP, and replayable evidence.

AI-native test engine for browser, API & MCP testing — 46 tools over Model Context Protocol. Built with Playwright + Bun.

An Model Context Protocol(MCP) server that generates comprehensive API test cases (positive, negative, edge cases) from endpoint metadata, powered by AI/LLMs

Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrate AI agents for auto-fix loops, and ship JUnit/JSON/HTML reports.

Run, validate, and automate APIs directly from OpenAPI — from the CLI, Go tests, or MCP agents.

HTTP/API testing tools for AI agents via MCP

A generic REST API tester for testing HTTP endpoints

MCP server that lets LLMs drive HTTPToolkit for automated API security testing — replay, mutation, and audit on captured mobile, desktop, and CLI traffic

API tests your AI writes and your CI runs: YAML files in your repository, one native binary, no account. A Postman alternative with a VS Code extension, a browser app and an MCP server for coding agents.

MCP Server of API Testing

The SandboxAPIs MCP server: read-only, API-compatible replicas of 21 developer APIs, preloaded with one simulated company, for testing agents without a test account.

Rate-Limit and API Stress Tester u2014 test, benchmark, fuzz, and monitor any HTTP API endpoint. 12 tools: burst testing, load profiling, auth testing, HAR replay, and more.

MCP server for testing: generate test cases, create mock data, mock API responses, analyze test coverage, generate assertions Install: npx @rog0x/mcp-testing-tools

An MCP server that provides Postman-like API testing capabilities for AI agents.

API testing for AI agents. From codebase to CI in one agent session.

Model Context Protocol server for Hoppscotch API testing platform

Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs. Build and test integrations and AI agents against a believable fake business, with resets, rewind, controllable time and failures on demand. No real accounts.

Browser automation and API testing MCP server built on Playwright + CDP. Numbered element refs and Set-of-Mark screenshots let AI agents target the right node; flow record/replay, element memory, captcha handoff and an HTTP API test suite.

TalkAPI: Conversational API testing MCP server for Claude Desktop. Test APIs through natural language - no Postman needed. Built by RAJ.

An MCP server that generates comprehensive API test plans (positive, negative, edge cases) from endpoint metadata.

Local, MIT-licensed AI test harness with 10 MCP tools and 11 prompts for risk-based test planning, focused testing, accessibility checks, evidence capture, screenshot maps and interactive HTML quality reports. Runs over stdio in one explicitly selected project. Your coding agent supplies AI and browser execution; CARBON records observed evidence and generates reports. No hosted backend, model API key or telemetry required.

server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.

A Model Context Protocol (MCP) server that exposes Specmatic's contract testing capabilities to AI coding agents like Claude Code. This server enables comprehensive API contract validation and mock server management for development workflows.

Interactive real-time debugging and testing for .NET APIs, SignalR hubs, and gRPC services in .NET, plus an MCP server for AI-hosted invocation workflows, delivered as a suite of NuGet packages.

MCP server for iOS app testing — see inside your running app: network calls, WebSocket frames, logs, storage, screen layout, and API mocking. Works with Claude Code, Cursor, Codex, Windsurf.

MCP server for the Ghost Inspector API — lets any MCP-capable agent triage, validate and safely repair end-to-end browser tests

Multimeter is an AI-powered REST Client and API testing tool for VS Code and CI. It is not an electrical multimeter. YAML .mmt files. testlight CLI. MCP @mmt/mcp. Git-native Postman alternative.

An MCP server that turns an agent's API testing into files you keep: it authors and edits Bruno collections in place, then runs them — HTTP, WebSocket and gRPC, one identity or many — and reports per-request pass/fail you can re-run in CI.

Free, API-keyless MCP for resilient web search and safe, visible Chrome automation—with dynamic companion status, forms, uploads, and WebGL testing.

A TypeScript-based MCP server that enables testing of REST APIs through Cline. This tool allows you to test and interact with any REST API endpoints directly from your development environment.

Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs. Build and test integrations and AI agents against a believable fake business, with resets, rewind, controllable time and failures on demand. No real accounts.

SeleniumBase for Rust (unofficial port): browser automation and testing with the SeleniumBase API, a driverless Chrome DevTools engine, stealth mode, and an MCP server for AI agents.

Local-first API collection studio with bundled local MCP, human-approved changes and guided API testing. Import, edit, test and export API specs.

107 production-grade QA engineering skills for AI agents — frontend, API, performance, mobile, security, CI, and AI/LLM testing. MCP-ready: works with Claude Code, Claude Desktop, Cursor, Zed, Windsurf, and any MCP host.

MCP server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.

MCP server for Zephyr Scale on self-hosted Jira Server / Data Center: test cases, cycles, executions, plans, folders, attachments and automation via REST API v1

Deterministic, zero-hallucination agentic QA engine. Equips AI agents with cognitive heuristics and boundary fuzzing to autonomously test Web, Mobile, Desktop, and APIs.

Stable since v1.0.0 — MCP server + cross-host agent skill (Claude Code / Codex / OpenClaw / Hermes) for QA testing across pytest / Jest / Cypress / Go / Maestro / Schemathesis / Newman, plus v1.1 Edge AI Runner (RTSP + YOLO). 22 frozen tools, bilingual EN/zh-TW QA knowledge, AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Top 10 (2023) scanner, universal qa_plan + verify bookend across 5 core tools (AI 測試大師)

MCP server for iOS app testing — see inside your running app: network calls, WebSocket frames, logs, UserDefaults, screen layout, and API mocking. Works with Claude Code, Cursor, Codex, Windsurf.

Task environments for AI agents working on .NET apps, as an MCP server: raise the app with its services on Nomad, call its API, read its logs, run its end-to-end tests, one environment per task. Native AOT ready.

MCP server for API testing: HTTP requests, endpoint health checks, JWT decode, URL parsing, security header analysis Install: npx @rog0x/mcp-api-tools

Robust, production tested MCP Server for linear (API)

One MCP server, a growing set of free public APIs, no API keys. Every tool tested by M3.

[pre-release, testing usage] A Model Context Protocol (MCP) server that enables AI Agents to request and manage Selenium browser instances through a secure API. Perfect for your automated browser testing needs! 🚀 [In development: creating usage examples and in-cluster setup]

MCP server and CLI that makes Claude Code, Codex and any coding agent better at Godot 4: offline Godot 4.7 API, project map, headless checks, an AAA GDScript review, safe edits and renames, GUT/GdUnit4 tests, play-testing with input, screenshots, and 3D m

Reverse engineer any API: discover how a website serves its data (publisher catalogs, OpenAPI, framework routes, APIs.guru, Wayback, CT, REA browser capture, jsluice, source maps, GraphQL), prove it with evidence, export OpenAPI 3.1, and generate tested T

MCP to Capture HTTP requests, emails, and DNS lookups test webhooks, debugg API callbacks

Unofficial third-party Sony DSC Camera Remote API client + Flask viewer + MCP server for AI-driven shooting (tested on DSC-RX100M5A). Not affiliated with Sony.

Production-validated MCP server for WhatsApp Business Cloud API — compliance engine, error intelligence & message orchestration for AI agents. 24 tools, sub-2ms decisions, 85.6% test coverage.