"A tool for improving the use and understanding of tools" matching MCP servers:

A zero-dependency Node.js playground for debugging how MCP clients authenticate to an MCP server over HTTP.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

A local MCP daemon that turns an agentic coding client into a bug bounty operator, with 103 tools for offensive security testing including MITM proxy, traffic analysis, and OOB callbacks.

Supply chain risk scoring for npm, PyPI, and GitHub repos

A stateless remote MCP server that lets AI agents anonymously submit encrypted reports of alignment and safety failures to leaks.md (what others did) and confession.md (what the agent itself did), returning a receipt without accounts or keys. It exposes public tools such as submit_leak and submit_confession over Streamable HTTP.

Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.

Enables declaring a catalog of tools for LLMs, filtering them by role, validating arguments, guarding sensitive calls with server-side confirmations, and recording an audit log.

A secure tool-execution plane for agentic AI that enforces JWT authentication, rate limiting, prompt-injection inspection, and audit logging, while ingesting downstream OpenAPI endpoints as MCP tools.

Protects AI agents from bad tool outputs, schema mismatches, and tool poisoning by validating, sanitizing, and scoring reliability of tool responses.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.

Enables agents to search across the pooled tools of many connected MCP servers and invoke them through a single endpoint, returning only the handful of tools relevant to each request. Filters by the caller's permissions before ranking, so agents never see or plan around tools their user is not allowed to use.

Enables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.

Governed MCP server for bank-grade agent tool access with RBAC, PII redaction, rate limiting, and audit logging.

Enables AI coding agents to run one-shot commands and copy single files to and from remote servers through The Bastion, which authenticates, authorizes, and records each action. Access is controlled by the bastion rather than allowlists or deny lists.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Demonstrates Agent Passport System pre-dispatch authorization by issuing one-use grants and verifying signed authorization envelopes before proxied tool calls reach the upstream server.

An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.

Enables AI agents to inspect any public domain’s web technology stack, email deliverability and DNS health (MX, SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI), and HTTPS security posture with typed JSON scores and remediation-ready findings, plus history, bulk checks, monitoring alerts, and reverse technology lookups.

Post-quantum readiness for AI coding agents: scans code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH) and returns NIST ML-KEM/ML-DSA/SLH-DSA (and hybrid) migration guidance, with fix verification and dependency checks. Content-based, advisory tools only; runs local (npx @quantakrypto/mcp) or as a hosted OAuth endpoint.

Enables AI agents to pay per call for live package-safety and GitHub merge-readiness trust signals via the x402 protocol.

A comprehensive suite of HTTP and API testing tools that enables AI agents to perform requests, check endpoint health, and decode JWTs. It also provides utilities for URL parsing and detailed security analysis of HTTP response headers.

Enables AI assistants to perform password security auditing using John the Ripper on a remote Kali system via SSH, supporting cracking, hash management, and session control.

Enables AI assistants to scan project dependencies and Infrastructure as Code files for security vulnerabilities and misconfigurations. It also provides automated fixing capabilities to remediate identified security issues.

Fork of @cyanheads toolkit MCP server. Added encoding functions, removed system network functions.

Exposes typed inventory reads and order preparation over MCP, with capability scopes enforced by the server process rather than tool arguments. Stock is committed only through a separate operator approval surface, keeping approval outside the model's reach.

Community MCP server for the Cymulate security validation platform. It exposes the full Cymulate REST API (337 endpoints) as 106 semantic tools for BAS, exposure validation, attack surface management, and platform administration.