Security & Testing MCP Servers for OpenAI Agents SDK

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs

Offline full-text search over the HackTricks security wiki, synced every 3 days.

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

MCP server for auditing AWS AI/ML workload security — Bedrock IAM, prompt injection signals, posture reports

The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.

Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats.

Every-click AI QA: walks your whole app from a preview URL and reports broken clicks and errors.

Lite Model Context Protocol server for comprehensive CVE intelligence gathering with multi-source exploit discovery, designed for security

Security scanning for websites, public repositories, and Open CLAW skills.

Drive a self-hosted Darkmoon Pro AI pentest instance: start runs, read campaigns and findings.

Dear User — helps humans and AI agents understand each other better

JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents

Minimal MCP server for Ghost Security API - compatible with all MCP clients

MCP server for the HackerOne Hacker API (Hackers section only). Built from https://api.hackerone.com/hacker-resources/

Drive the iOS Simulator via semantic accessibility-tree snapshots. Sub-200ms, no WebDriverAgent.

Detect fake-recruiter and job-offer scams using free OSINT. No API keys.

Static blast-radius audit for MCP servers before agent install. Manifest optional.

Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.

Modular AI-assisted network security audit platform — Community Edition