mcp-testing-tools
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-testing-tools Generate tests for fetchUser(id: number): Promise<User>"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@rog0x/mcp-testing-tools
Testing and quality assurance tools for AI agents, exposed via the Model Context Protocol (MCP).
Tools
generate_tests
Generate test cases from a function signature. Produces four categories of tests as ready-to-run Jest or Vitest code:
Happy path -- valid inputs, expected outputs
Edge cases -- empty strings, zero values, null parameters
Error cases -- missing arguments, wrong types
Boundary values -- extreme numbers, large arrays, NaN
Parameters:
Name | Type | Required | Description |
| string | Yes | Function signature, e.g. |
| string | No |
|
| string | No | Import path for the module under test (default: |
generate_mock_data
Generate realistic mock data for testing. Supported types:
name, email, address, date, uuid, phone, company, credit_card, ip
Parameters:
Name | Type | Required | Description |
| string | Yes | Data type to generate |
| number | No | Number of items (default: 10, max: 1000) |
| string | No |
|
| string[] | No | Generate mixed records with multiple field types |
generate_api_mock
Generate mock API responses from a schema definition. Creates realistic JSON payloads for REST endpoints by inferring values from field names and types.
Parameters:
Name | Type | Required | Description |
| string | Yes | API endpoint path |
| string | No | HTTP method (default: |
| object[] | Yes | Field schemas with |
| number | No | Number of records (default: 1, max: 100) |
| number | No | HTTP status code (default: 200) |
| boolean | No | Wrap in |
analyze_test_coverage
Analyze source code and test code to find untested functions. Prioritizes suggestions by:
Export status (public API surface)
Cyclomatic complexity estimate
Parameter count
Async functions (more error paths)
Parameters:
Name | Type | Required | Description |
| string | Yes | Source code to analyze |
| string | Yes | Existing test code |
| string | No | Filename label (default: |
generate_assertions
Generate detailed assertion code by comparing expected and actual values. Performs deep diff and produces per-field assertions with descriptive comments.
Parameters:
Name | Type | Required | Description |
| string | Yes | Expected value as JSON string |
| string | Yes | Actual value as JSON string |
| string | No | Description for the comparison |
| string | No |
|
| boolean | No | Deep equality for objects/arrays (default: true) |
Related MCP server: EvalView
Setup
npm install
npm run buildUsage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"testing-tools": {
"command": "node",
"args": ["path/to/mcp-testing-tools/dist/index.js"]
}
}
}License
MIT
Available Tools
5 toolsanalyze_test_coverageA
Parse source code and test code to identify untested functions. Suggests which functions need tests most based on complexity, export status, and parameter count.
Inputs: test_code (required), source_code (required), source_file_name.
generate_api_mockB
Generate mock API responses from a schema. Creates realistic JSON responses for REST endpoints based on field names and types.
Inputs: fields (required), endpoint (required), count, method, +2 more.
generate_assertionsA
Given expected and actual values (as JSON strings), generate detailed assertion code with descriptive messages. Supports deep object comparison, array comparison, and type checking.
Inputs: actual (required), expected (required), deep, label, +1 more.
generate_mock_dataA
Generate realistic mock data: names, emails, addresses, dates, UUIDs, phone numbers, company names, credit cards (fake), IP addresses. Configurable count and locale.
Inputs: type (required), count, types, locale.
generate_testsB
Generate test cases from a function signature. Produces happy path, edge cases, error cases, and boundary value tests as Jest/Vitest test code.
Inputs: signature (required), framework, module_path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Most tools have clearly distinct purposes, but generate_tests and generate_assertions overlap slightly since generated test cases often include assertions. generate_mock_data and generate_api_mock are similarly related, though the former is general-purpose data and the latter is schema-driven API responses.
All tool names follow a consistent verb_noun pattern: generate_tests, generate_mock_data, generate_api_mock, generate_assertions, and analyze_test_coverage. The naming convention is uniform and predictable.
Five tools is a well-scoped set for a testing-focused server. Each tool covers a distinct aspect of test generation, mocking, assertions, or coverage analysis without unnecessary redundancy.
The tool surface covers test generation, mock data, API mocking, assertions, and coverage analysis well. Minor gaps exist, such as no direct test execution or test file management, but the core testing workflow is addressed.
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Test management for AI agents: cases, runs, results, cycles and traceability.
152 free QA tools for agents: injection scan, evals, RAG, web audits. Smaller packs: /mcp/{pack}.
Related MCP Servers
- AlicenseAqualityBmaintenanceA specialized testing harness that enables AI assistants to thoroughly test other MCP servers by connecting to them, discovering their tools/resources/prompts, executing test calls, and performing end-to-end validation with LLM integration.144MIT
- AlicenseAqualityAmaintenanceMCP server that lets coding agents test AI agents. Create YAML test cases, snapshot golden baselines, check for regressions, and generate visual reports all from inside Claude Code or any MCP-compatible tool. Works with LangGraph, CrewAI, OpenAI, Claude, Mistral, and any HTTP API.101,798 PyPI142Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI agents to programmatically inspect, test, and validate other MCP servers by exposing MCP Workbench capabilities as structured tools. It supports automated test spec generation, execution, and detailed failure analysis to ensure server reliability.47 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceAll-in-one automation platform for AI agents, providing browser automation, API testing, debugging, and testing tools via the MCP protocol.3MIT