TestMind
Open-source intelligent testing AI platform. MCP Server + Agent hybrid architecture — let AI generate, execute, and analyze your tests.
Why TestMind?
- 🤖 AI-Driven: Claude Code / OpenCode / Cursor act as the "brain" — they understand your API specs and generate high-quality test cases.
- ⚡ Dual Mode: Use Agent + MCP for AI-powered workflows, or CLI standalone for CI/CD pipelines with zero AI dependency.
- 🔌 MCP-Native: Built on the Model Context Protocol — any MCP-compatible agent can drive TestMind out of the box.
- 📐 Spec-Driven: Point at an OpenAPI/Swagger spec, and TestMind generates structured, maintainable test cases automatically.
Quick Start
# Install
pip install testmind-ai
# Initialize a new test project
testmind init my-project --type api --base-url https://api.example.com --agent claude
# Discover and parse your API spec
testmind discover-spec https://api.example.com
testmind fetch-url https://api.example.com/openapi.json
testmind parse-spec specs/openapi.json
# Run tests
testmind run --env dev --tags smoke
# View results
testmind results --status fail
# Start MCP Server (for AI agent integration)
testmind serve
Architecture
┌──────────────────────┐ MCP Protocol ┌──────────────────────────────┐
│ AI Agent (Brain) │ ◄──────────────────► │ TestMind MCP Server │
│ Claude / OpenCode │ │ • 18 MCP tools │
│ Generate, Analyze, │ │ • Spec parsing │
│ Strategy decisions │ │ • Case execution │
└──────────────────────┘ │ • Results analysis │
│ • Security scanning │
│ • Performance benchmarking │
┌──────────────────────┐ └──────────────────────────────┘
│ TestMind CLI │
│ Zero AI, pure exec │ │ HTTP
│ For CI/CD pipelines │ ┌──────────────────────────────┐
└──────────────────────┘ │ Your API / Web App │
└──────────────────────────────┘
Features
Core Engine
- Runner: Topological sort, concurrent execution, retry, fail-fast, env filtering
- Assertions: status_code, jsonpath, header, response_time, json_schema, body_contains, custom
- Variables: 5-tier priority system + built-in functions (timestamp, uuid, random, etc.)
- Hooks: before/after, setup/teardown at project/suite/case level
MCP Tools (18 total)
| Category | Tools |
|---|---|
| Spec | discover_spec, fetch_url, parse_spec, save_spec, save_requirements |
| Execution | validate_case, save_case, run_cases, get_results, list_cases |
| Project | init_project, get_config |
| Web UI | browser_navigate, browser_click, browser_type, browser_screenshot, browser_get_text, browser_close |
CLI Commands
testmind init # Create new project
testmind run # Execute test cases
testmind results # View test results
testmind analyze # Analyze trends & failures
testmind perf run # Performance benchmarking (p50/p90/p95/p99)
testmind security scan # SQL injection, XSS, path traversal scanning
testmind suite create # Group cases into suites
testmind approve # Review & approve pending cases
Installation Options
# Core installation
pip install testmind-ai
# With crypto support (encrypted secrets)
pip install testmind-ai[crypto]
# With web UI testing (Playwright)
pip install testmind-ai[web]
# Full development setup
pip install testmind-ai[dev,crypto,web]
Project Structure (after testmind init)
my-project/
├── testmind/
│ ├── project.json # Project config
│ ├── envs/ # Environment configs (dev/staging/prod)
│ ├── specs/ # API specifications
│ ├── cases/ # Test cases (JSON)
│ ├── suites/ # Test suites
│ ├── hooks/ # Custom hook scripts
│ ├── results/ # Execution results + HTML reports
│ └── logs/ # Audit & run logs
├── .claude/ # Claude Code integration (auto-generated)
├── .opencode/ # OpenCode integration (auto-generated)
└── .cursorrules # Cursor rules (auto-generated)
Requirements
- Python 3.10+
- No external services required — runs entirely locally
License
MIT © TestMind Team
Metadata
Release files for testmind-ai 0.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| testmind_ai-0.5.0.tar.gz | 103.9 kB | Without provenance | Details for testmind_ai-0.5.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| testmind_ai-0.5.0-py3-none-any.whl | Python 3 | none | any | Details for testmind_ai-0.5.0-py3-none-any.whl |
Total release size: 243.0 kB
Release files / testmind_ai-0.5.0.tar.gz
| Download URL | testmind_ai-0.5.0.tar.gz |
|---|---|
| Size | 103.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
67c46f7ffa76bbf816c5340a919b4d1aa85933947fda70f4b13f2328ddab8d98
|
|
BLAKE2b-256 checksum How to use checksums |
7d327755375a4f51904ede0c0716fe5fc54290ad34cf85f1bf02e38e71361faa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.0
|
Release files / testmind_ai-0.5.0-py3-none-any.whl
| Download URL | testmind_ai-0.5.0-py3-none-any.whl |
|---|---|
| Size | 139.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a9767c67c3d627d3535cb503fa90022c9da2c55c94d959f3ddf3b8cae24d96da
|
|
BLAKE2b-256 checksum How to use checksums |
42ee6580378267dc8c0cd36ddd9e4c93553dc272a76df415e977d5666cc3c6c7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.0
|
Security for testmind-ai 0.5.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.