Metadata-Version: 2.3
Name: toolwall
Version: 0.2.0
Summary: Fail-closed firewall for AI agent tool calls: schema + policy gate before any tool executes
Project-URL: Homepage, https://github.com/Dev-Saif-Ops/Project_TOAP
Author: Mohammad Safwan Athar
License: MIT
Keywords: agents,ai,guardrails,llm,mcp,security,tool-calling
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Provides-Extra: dev
Requires-Dist: pytest-cov>=4.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Provides-Extra: mcp
Requires-Dist: mcp>=1.0.0; extra == 'mcp'
Description-Content-Type: text/markdown

# toolwall (package)

Fail-closed firewall for AI agent tool calls. See the [repo README](../README.md) for the full story.

```bash
pip install -e .
python examples/quickstart.py   # no API key needed
pytest                          # run the suite
```

## Modules

| Module | Role |
|---|---|
| `intake.py` | Normalize OpenAI / Anthropic / Gemini / plain-dict tool calls |
| `gate.py` | Fail-closed check → verdict → (optional) execute |
| `schema.py` | Required args + type validation before `tool(**args)` |
| `meter.py` | Audit events, token/cost accounting, JSON/CSV export |
| `cli.py` | `toolwall report <audit.json>` |
