Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — cross-platform desktop app powered by Spring AI.

Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — cross-platform desktop app powered by Spring AI.

A deny-by-default contract & type-checker layer for AI agent tool calls — Pydantic-based, in-process, zero-core-deps. Validates the actual tool-call payload (ghost-arg stripping, strict types, self-healing retries) beneath MCP gateways & firewalls. Works with LangChain, OpenAI Agents SDK, PydanticAI & CrewAI.

🛡️ Open-source safety guardrail for AI agent tool calls. <2ms, zero dependencies.

MCP server: validate tool-call args before execution. Wraps @mukundakatta/agentvet.

Block prompt injection, path traversal, SQL injection, and more — before your agent's tools execute. Zero deps, sub-millisecond.

GitHub Action that lints LLM tool definitions (Anthropic / OpenAI / MCP shapes). Wraps @mukundakatta/agentvet.

Python port of @mukundakatta/agentvet: validate LLM-generated tool args before execution

Validate LLM-generated tool args before execution. Wrap your tools with a schema; throws ToolArgError with an LLM-friendly retry hint. Zero deps.