Search

MCP server for secure AI agent authentication — lets Claude, Claude Code, and other LLM agents call APIs without exposing raw tokens or credentials to the model

Assay — a canary-oracle benchmark for MCP security: a frozen task set scored by a recomputable HMAC-canary oracle (structural-zero false positives), not an LLM judge. Maintained by Verosek.

MCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catches prompt injection, tool poisoning & credential exfiltration.

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.

MCP security patterns — 10 production implementations mapped to OWASP MCP Top 10. Prompt injection, credential isolation, HITL governance, session recording. Working attack demos included.

Zero-trust runtime security gateway for MCP: intercepts every tool call, blocks prompt injection, exfiltration, rug-pulls & destructive ops before they execute. Deterministic policy decides — AI only advises.

LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles the AgentGuards MCP server plus enforcing hooks.

Security gateway for MCP agents: blocks prompt-injection-driven tool calls (poisoned payments, fabricated results) with cryptographic receipts, value-provenance enforcement, and multi-model consensus. The verification layer no syntactic MCP firewall has.

CStrike v2.6 — Offensive Security Platform. 35+ tools, 9-container Docker stack, self-update system, parallel port scanning, VPN kill-switch. Dual-arch (amd64/aarch64) VM distribution.

The open-source firewall for AI agents. Block prompt injections, jailbreaks, and data leaks before they reach your LLM. Multi-layer defense, agent-era security (MCP/Capability), US/CN/JP/EU compliance. Zero-dependency core.

Vendor-neutral benchmark measuring how MCP security proxies/gateways DEFEND against 22+ attack vectors — crosswalked to NIST AI RMF & OWASP LLM/Agentic Top 10. CI-gated, reproducible, DOI-cited. Submit your tool to the leaderboard.

Agentic security CLI that finds reachable vulnerabilities, writes the fix, and attacks its own patch in an isolated Nebius sandbox. A patch is certified only when the live exploit fails. Powered by NVIDIA Nemotron on Nebius Token Factory. Works as a CI gate and MCP server.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

Immune — the agent security loop that turns every attack into an antibody. MCP firewall → replayable breach trace in ClickHouse → synthesized countermeasure → replay-proven → Semgrep rescan → signed receipt → ruling → the next agent is immune. Built at the Cyberdefense Hackathon, SF Tech Week 2026.

SecureMCP is a security auditing tool designed to detect vulnerabilities and misconfigurations in applications using the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction). It proactively identifies threats like OAuth token leakage, prompt injection vulnerabilities, rogue MCP servers, and tool poisoning attacks.

Blackwall LLM Shield is an open-source AI security toolkit for JavaScript and Python that protects LLM apps from prompt injection, sensitive data leaks, unsafe tool calls, and hostile RAG content with prompt sanitization, PII masking, output inspection, policy enforcement, and audit trails.

AI-Infra-Guard is Tencent’s open-source AI red-teaming platform for scanning AI agents, MCP servers, agent skills, AI infrastructure, and LLM jailbreak exposure before deployment. It combines platform workflows, Docker deployment options, APIs, and extensible security rules for AI-specific risk review.

Thick client penetration testing and MSIX security audit toolkit for Windows. Audits .NET, Electron and native binaries: static and runtime checks, IL-verified findings, computed CVSS v4.0, CWE/ATT&CK mapping, SBOM, HTML/Excel reports. PowerShell engine, GUI, MCP server and agentic AI triage.

[](https://glama.ai/mcp/servers/sint-ai/sint-protocol) 📇 🏠 🍎 🪟 🐧 - Security-first MCP governance proxy (`sint-mcp`) with capability tokens, T0-T3 approval tiers, fail-closed execution, and tamper-evident audit receipts. Includes a separate `sint-scan` CLI for preflight MCP tool-risk audits.

Curated list of open-source AI security tools and resources