MCP servers for security

⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation. 57 escalation chains, 130-

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Zero-trust security gateway between AI agents and MCP servers: scoped capabilities, redaction, rate and cost limits, and verifiable session logs.

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

Remote hands for coding agents: an MCP server that runs OpenCode / Claude Code / Codex work on a remote host over SSH, keeps credentials and the local machine closed, and audits everything

The AI-operated escrow court and reputation protocol for the agentic economy.

MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads

Local CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.

Pre-production checklists for solo founders. 4,337 items, 88% portable to any stack, 26 stack supplements — plus AI/agent security and the bugs AI coding assistants actually write.

Local credential control for AI coding agents.

GenPark AI Agent Skill - AST security pattern matcher for injection vulnerabilities, insecure deserialization, secret leakage, and safe code rewrite synthesis.

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

GenPark AI Agent Skill - High-speed PII and secret redaction engine with reversible token vault and credential sanitization.

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

GenPark AI Agent Skill - High-speed PII and secret redaction engine with reversible token vault and credential sanitization.

GenPark AI Agent Skill - AST security pattern matcher for injection vulnerabilities, insecure deserialization, secret leakage, and safe code rewrite synthesis.

Cryptographic JSON Web Token (JWT) engine with RFC 7519 HMAC-SHA256 signature verification, claims validation, and expiration enforcement.

Side-channel timing attack defense primitive providing constant-time bitwise and string digest comparison for agent security credentials.

Cryptographic JSON Web Token (JWT) engine with RFC 7519 HMAC-SHA256 signature verification, claims validation, and expiration enforcement.

Interactive Schnorr Zero-Knowledge Identification (ZKP) protocol proving private key knowledge via 3-pass commitment, challenge, and response.

Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation

AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green

Capgate — runtime authority boundary for autonomous AI agents: the agent proposes, the harness authorizes, the executor acts. Deny-by-default policy, non-transitive delegation, tamper-evident audit, M

A local-first permission firewall and approval layer for AI agent tool calls.

Security scanner for Claude Code skills, plugins, and MCP servers. A verdict before you install.

Give ChatGPT fast, safe, and auditable visibility into your VPS through MCP.

The agent-native Supabase killer: SQLite speed today, distributed cloud next, without the PostgreSQL tax.

An MCP tool. Connect your assistant to /mcp and every tool call goes through a broker — scoped per caller, under a credential they never hold, revocable, metered and audited.

Native macOS network monitor: every app's traffic to every domain, plus AI agent oversight with per-agent allowlists and tool/MCP server attribution. Free, open source (GPL-3.0), no telemetry.

A lightweight, sub-millisecond security shim that prevents AI agents from accessing sensitive files (.env, SSH keys) and executing destructive commands via MCP.

⚡ Autonomous reverse engineering engine & Model Context Protocol (MCP) server for binaries and applications in Systems Rust

Sandboxed security scanning for AI skills and MCP servers — precise findings, heatmap posture, fail-closed agent guard. Multi-scanner security platform for AI skills and MCP servers, scan what the age

Cryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.

A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.

Universal MCP server: connect any OpenAPI/Swagger, GraphQL, gRPC or SOAP API to AI agents. Security-first, local, token-efficient. Any API. One server.

🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.

Scan MCP servers & AI-agent skills for malicious patterns (prompt injection in tool descriptions, credential exfil, download-and-execute). 17 patterns / 60 signatures, zero-dep. Measured over 196 publ

Security-guarded MCP server for Bugzilla, written in Rust

Governance for agent instructions: audit, score, and pin MCP servers, Agent Skills, and prompts. Deterministic; findings carry a reference and a fix.

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default,

Fast single-binary security scanner for MCP (Model Context Protocol) servers — config audit, live capability enumeration, tool-poisoning detection & risk grading. Zero deps, fully offline — trivy for

Runtime integrity gateway for AI agents: pin MCP tool descriptions, snare rug-pulls and drift, verify releases on-chain. Zero-dep.

Audit and revoke everything Claude Code has been given on Linux: trusted folders, "always allow" rules, saved transcripts, hooks, MCP servers. Quarantine instead of delete, one command to undo. Single