Search

MCP server that scans Agent2Agent (A2A) protocol implementation code for anti-patterns found in the reference SDKs and sample agents: unauthenticated push-notification webhook fetches (SSRF), Agent Cards with no authentication requirement, and credentials

MCP server that scans other MCP servers' tool definitions for tool poisoning (hidden instructions embedded in a tool's description, read as trusted context by the calling LLM) and confused-deputy mismatches (a tool's name/description promises read-only be

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes. Apache 2.0

Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP server for Claude, Cursor, VS Code, Xcode, JetBrains.

Platform binary for vestige-mcp-server (do not install directly).

MCP server that scans documents, scraped pages, and RAG content for indirect prompt injection payloads — instruction-override phrases, spoofed chat-template roles, hidden/invisible text, content addressing the AI directly, and data-exfiltration attempts

Vestige MCP Server - AI Memory System for Claude and other assistants

Static analysis for AI and agent code: Python, TypeScript, JavaScript, MCP manifests and live servers, Skills, and dependency CVEs.

Trust verification CLI for AI packages — check MCP servers, A2A agents, and AI tools before you install

Free, zero-dependency 15-attack prompt-injection / jailbreak smoke test for your own LLM endpoint.

A transparent audit proxy for MCP servers: records every tool call, detects tool poisoning and rug pulls

Audit MCP configs and servers for risky tools, secret exposure, and prompt-injection patterns.

A framework for building and running your own living GenAI/LLM threat model. Ships with a curated reference catalog, an LLM-driven assessor, and an MCP server

Free, zero-dependency 15-attack prompt-injection / jailbreak smoke test for your own LLM endpoint (OWASP LLM Top 10), plus a static MCP tool-manifest heuristic scanner (`sentinel-scan mcp`).

Pre-install safety, token, and maintainability scorecard for AI agent skills.

Core CLI for Assurly production readiness verification

MCP package manager with trust scoring. Search, install, and audit MCP servers.

No description available

Deterministic registry + integrity scanner for Model Context Protocol servers. Make MCP supply-chain boring.

Checks robots.txt line by line and says what each AI crawler token actually controls - training, AI-search citation, or user fetch - and which lines silently do nothing.