Search

Python security scanner with Model Context Protocol (MCP) integration for AI assistants

MCP server that scans MCP configurations, tool definitions, and code for security vulnerabilities

What can this MCP server actually do — and has it changed since you trusted it? Inspect its declared capabilities, seal them in a lock file, and get told when a later version can do more. Never invokes a tool; gives the server a minimal environment.

Audit AI agent configs for prompt injection & rogue MCP servers; vet packages

Let AI agents work autonomously. Memnox rules on every tool call Claude Code, Codex, Cursor, Gemini CLI and Windsurf make, before it runs: allow, ask or deny. Runs on your machine, needs no account, and no model decides anything. npm install -g memnox

Catch hard-coded secrets, insecure URLs, missing env vars, and unpinned packages in MCP configs.

Every AI skill, independently scanned. Coming soon. See https://github.com/OpenLatch/saferskills.

生成AIを社外のMCPサーバやAPIにつなぐ前に、ツール定義の汚染・差し替え、過剰な権限、既知脆弱性を審査し、許可／条件付き許可／不可を判定するツール。Azure API Center と連携した自動審査に対応

Open-source tool for discovering, extracting, and visualizing permissions used by AI agents and MCP servers.

Zero-dependency JavaScript-based AES-256-GCM encryption for text, files & WebRTC E2EE. Includes symmetric (password) and asymmetric (RSA-4096 hybrid) modes. Streaming, quantum-resistant key derivation, pure Web Crypto API.

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets poisoned docs compromise developer projects without warning.

Read-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.

Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced read-only queries, PII masking, human-approved writes, a tamper-evident audit log, a red-team suite and Terraform for Cloud Run.

Read-only VibeRaven guides: explain a finding, search launch guides, get a Supabase checklist.

Install AI-agent Skills & MCP servers with a verified, independent SaferSkills trust score — across Claude Code, Cursor, Windsurf, Copilot, Codex, Gemini, Cline & OpenClaw.

Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.

Check npm/PyPI packages exist and that a function or method exists in an exact package version.

Deepsleuth — read the fine print. Deterministic deep-visibility security scanner for MCP servers (no LLM).

Local-first control plane for governing AI agent runtime behavior, from preflight risk checks to live mediation and post-run audit.

Wazuh MCP Server: AI-Driven SOC Automation