"A design and prototyping tool - Figma" matching MCP servers:

Enables AI assistants to natively execute and manage 600+ Kali Linux security, penetration testing, and forensic tools, including search, help documentation, structured scanners, and workspace management.

MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.

Cyber Host Artificial Intelligence (C.H.A.I) An autonomous penetration testing MCP (Model Context Protocol) server with an integrated AI decision engine, multi-provider LLM support, and an extensible plugin architecture.

Enables auditing and monitoring of AI agent MCP tool calls, with behavioral anomaly detection, lab-scoped red-team simulation, and Telegram notifications.

Enables agents and operators to audit MCP tool permissions for least privilege, score blast radius, detect privilege-escalation chains, verify capability matrices, and produce cryptographic audit proofs with injection fuzzing and exfiltration canaries.

Enables real-time injection fuzzing, exfiltration canary detection, least-privilege tool sandboxing, and cryptographic audit proofs through the Model Context Protocol.

Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.

MCP security firewall (stdio): vet advertised tool definitions through static-scan → threat-feed → origin → pinning before they reach the model. Zero npm runtime deps. No secrets.

SkillTotal is a local stdio MCP server that lets an agent check a component before installing it. It statically analyzes MCP servers, agent skills, npm/PyPI packages and repos for supply-chain risks, dangerous capabilities (shell, filesystem, network, credentials), prompt-injection surfaces like tool poisoning, and exfiltration paths. Each finding cites file, line and snippet.

Agent-native "safe to ship?" security gate for AI-generated code. Uses real parsers and inter-rocedural taint analysis (JS/TS, Python, Go) to flag the classes AI coding agents get wrong — secrets, SQL injection, SS, SSRF, path traversal, command injection, weak JWT/CORS — and ranks findings by confidence. Exposes a scan tool over MCP.

Open behavioral litmus for MCP servers — grades A–F across tool-output injection, egress, sensitive-data, and adversarial-input, with reproducible, content-addressed evidence. Tools: run_litmus, verify_attestation.

Provides a generic HTTP client tool allowing AI agents to make arbitrary HTTP requests from their environment, with support for environment-variable placeholders for secrets.

Provides security audit primitives for MCP servers, agent tool schemas, and system prompts, along with pentest utilities like JWT inspection and HTTP diffing.

Scans MCP servers for prompt-injection, tool-poisoning, and SSRF vulnerabilities using 30+ canonical rules across 5 severity tiers, with optional signed safety reports for procurement.

Enables AI assistants to run read-only exposure scans against MCP servers that front databases, surfacing unauthenticated access, role/tool leaks, write-capable tools, and locally stored credentials, then returning plain-language findings.

Chrome browser JS reverse engineering MCP tool for CTF/Web security, enabling dynamic analysis and restoration of login encryption logic.

Enables AI assistants to perform domain reconnaissance using theHarvester OSINT tool, including email harvesting, subdomain discovery, DNS brute force, and Shodan integration, via SSH on a Kali Linux host.

Security scanner for MCP servers that detects tool poisoning, shadowing, and other risks via static rules and semantic analysis. Exposes the scan_mcp_server tool for scanning MCP servers over stdio.

AI-powered penetration testing reasoning engine (MCP server) for attack path planning, step scoring, and tool recommendations using Beam Search and Monte Carlo Tree Search.

An MCP server that provides safeguard capabilities to protect against prompt injection and unsafe tool calls.

Enables security inspection of MCP tool metadata by analyzing tool names, descriptions, and input schemas, and returning SAFE, REVIEW, or HIGH RISK verdicts through the analyze_tools tool.

A tool that allows penetration testing through Kali Linux commands executed via a Multi-Conversation Protocol server, supporting security testing operations like SQL injection and command execution.

Enterprise-grade zero-dependency security shield and runtime governance engine for MCP servers, providing OWASP MCP Top 10 audits, cryptographic tool call signing, AIBOM generation, and inline parameter firewall protection.

Provides AI agents with structured access to the OWASP Bug Logging Tool (BLT) ecosystem for logging bugs, triaging issues, and managing security workflows. It enables actions like submitting vulnerabilities, tracking contributor leaderboards, and awarding gamified bacon points through a unified interface.

An authorization-first MCP-governed control plane for executing security-tool workflows in explicitly approved, sandboxed environments with auditable campaigns and AI collaboration boundaries.

A security research MCP server for testing tool call safety with deterministic policies like allowlists, path boundary enforcement, SSRF prevention, output redaction, and prompt injection detection, without requiring external LLMs or API keys.

A security testing tool that enables automated vulnerability detection including XSS and SQL injection, along with comprehensive browser interaction capabilities for web application penetration testing.

Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.

Enables read-only security assessment of a public MCP endpoint by sending initialize and tools/list requests and returning a 0–100 score covering transport, auth, overly broad tools, injection phrasing, and rug-pull definition changes, plus a 12-probe prompt-injection suite against a bot you own that flags leaked system prompts, tool dumps, secrets, exfiltration channels, and canary obedience.

A self-hostable, vulnerable-by-design MCP server for learning how object-level authorization bugs (BOLA/IDOR) appear in multi-tenant tools.