Search

Find out what your AI agents can actually reach. Maps every agent, MCP server, and skill on a machine or repo to the credentials, files, and systems it can touch — then draws the blast radius.

Input sanitizer for AI agents — anti-prompt-injection shield

Policy-enforcing MCP proxy with portable evidence output.

MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust

Runtime governance proxy for MCP servers. Risk scoring, hash-chained audit, per-tenant policy.

A 135+ tool DFIR toolkit, a live self-updating threat-intel platform, and a 332-tool MCP server — on one Cloudflare Workers deploy. MIT licensed. Portfolio: pranithjain.qzz.io

Governed database access for AI assistants: masking, signed receipts, coverage reconciliation.

Governance for AI agents: a deny-by-default policy layer for Claude Code and agent/skill builds. Every tool call is authorized, contained, and audited. Apache-2.0.

Stop MCP servers from rug-pulling your AI agent. A lockfile + runtime reference monitor for MCP tools.

IAM Policy Autopilot is an open source static code analysis tool that helps you quickly create baseline AWS IAM policies that you can refine as your application evolves. This tool is available as a command-line utility and MCP server for use within AI coding assistants for quickly building IAM policies.

MCP server exposing Koma Gate prompt-injection classification as a tool for AI agents.

Pytest plugin for testing chatbots and LLM apps — prompt injection, jailbreaks, system-prompt leaks, hallucinations, brand drift.

Compact Model Context Protocol server for hexvero analyzers.

Layered Network Substrate for Agent Telemetry - AI agent governance and policy enforcement layer for MCP, APIs, CLIs, and tools: scoped authorization, human approval, execution boundaries, and audit evidence. Pre-release.

MCP Proxy — runtime interception for AI agent tool calls using ATR rules

AgentGuard SDK — policy engine, audit trail, kill switch, and LangChain/OpenAI integrations

Capability gating for MCP agents, and the measurements that argue for it

Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.

The on-device guardrail for agentic AI. Let AI agents (Claude, Codex/ChatGPT, Cursor, any MCP client) touch your files — without the risk. Blocks dangerous actions, refuses your secrets, and keeps a tamper-proof audit log. Runs entirely on your machine; works offline.

See what your AI agents can cause, route them safely, and prove what happened. Open-source execution authority for AI agents — consequence preview, trust routing, signed receipts.