"Local Health Risk and Safety Guidance for COVID-19, Flu, RSV, and Other Illnesses in the US" matching MCP servers:

Enables AI agents to check URL safety before fetching content, using Google Web Risk, URLhaus, PhishTank, and AI analysis to return SAFE/SUSPICIOUS/DANGEROUS verdicts.

Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.

Enables security scanning of code projects to identify common vulnerabilities like XSS, injections, SSRF, and path traversal issues. Provides local, offline scanning with severity-grouped results and actionable fix suggestions for improving code security.

MCP server for sovereign US legal workflows, providing Ed25519-signed manifests and offline-capable access via your own infrastructure.

Performs comprehensive crawler compliance risk assessment for webpages, evaluating legal, ethical, and technical risks including robots.txt rules, anti-crawling mechanisms, sensitive data detection, and providing crawl permissibility ratings.

Enables CVE lookups and risk assessment by integrating CISA Known Exploited Vulnerabilities (KEV) data and CVSS metrics. It helps users prioritize patching efforts by ranking vulnerabilities based on exploitation status and calculated risk scores.

Wraps @ai-native-solutions/fallarch-us-sdk as an MCP stdio server for sovereign, Ed25519-signed professional-service workflow management.

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.

Replay safety evals before agent releases move forward. A paid remote MCP for AI agent safety replay checks, policy gates, eval receipts, control-fix suggestions, and release evidence exports.

An MCP server that provides AI agents with real-time package health data, vulnerability reports, and dependency graphs from PyPI and OSV.dev.

A sovereign, MIT-licensed MCP server that provides cryptographically signed notarization for listings, benchmarks, and transactions using Ed25519. It runs offline on user infrastructure as a free alternative to SaaS notary tools.

Enables scanning projects for dependency vulnerabilities, secrets, license conflicts, code quality, and git health, returning a 0-100 health score with actionable suggestions.

Provides MCP tools to check a package's maintenance status, licence, and security advisories before you depend on it, with per-call payment in USDC on Base mainnet via x402.

Monitors and analyzes dependency health in Node.js projects, providing tools to check outdated packages, vulnerabilities, licenses, and suggest safe upgrades.

Risk Assessment AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Local-first Gmail MCP server using PKCE + loopback OAuth flow that stores refresh tokens in the OS keychain, enabling secure read/write Gmail access via MCP tools without tokens leaving the device.

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.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

A secure MCP server that allows Claude to read and write local files on your machine with explicit approval gating for each access.

Provides audit_plugin_health and prepare_semantic_review tools for deterministic inspection of Codex plugins and Agent Skills, generating evidence-backed reports without executing or transmitting target code.