Search

Security scanner for MCP servers. Detects tool poisoning, prompt injection hidden in tool descriptions, leaked API keys, and supply-chain risk across Claude, Cursor, VS Code, Windsurf and Zed configs. One command, no API key.

MCP server for security code review: prompts, checklists, quick scans and persistent security reports

Adversarial security review for AI skills, repos, MCP servers, and packages before you install them. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO WITH MITIGATIONS / NO-GO verdict.

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

Secure mcp infrastructure to audit and control every data access by AI agents with minimal efforts

MCP server for security code review: prompts, checklists, quick scans and persistent security reports

MCP server that detects toxic flows (lethal trifecta) across an MCP tool catalog — untrusted content + private/sensitive data + exfiltration or destruction on the same server

The firewall for AI agents (preview): fixed rules, outside the model, check each tool call that reaches them through a coding agent's hooks, the library or the MCP gateway, before it runs.

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

Detect and strip malicious prompt injection, jailbreaking, and data exfiltration attempts from LLM inputs. Zero dependencies. Works in Node.js and browsers.

MCP server that scans ML model files (PyTorch, pickle, safetensors, Keras/H5, ONNX) for supply-chain risks — malicious pickle deserialization gadgets, disguised/malformed safetensors headers, Keras Lambda-layer RCE, and ONNX external-data path traversal

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

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.

MCP server that scans LLM/agent application code for Unbounded Consumption ("denial of wallet") anti-patterns from OWASP LLM Top 10 2026's #6 category: missing output token limits, missing timeouts on hand-rolled LLM HTTP calls, unbounded agent tool-calli

HuggingFace Inference API connector for BonkLM - Model input/output validation

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

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

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

Find it. Break it. Fix it. The hacker's toolkit for AI agents.

Red teaming framework that proves whether an MCP agent can be hijacked