Security MCP servers
Security MCP servers for scanning, threat intelligence and audits: let an AI assistant check code, dependencies and infrastructure for risks. 3.540 servers in dieser Kategorie.
Security MCP servers for scanning, threat intelligence and audits: let an AI assistant check code, dependencies and infrastructure for risks. 3.540 servers in dieser Kategorie.
Füge das GitHub Repo ein und wir listen ihn nach einem kurzen Review auf.
Server einreichenPerform OSINT investigations and threat intelligence lookups for domains, IPs, URLs, and business records with traceable evidence.
$claude mcp add --transport http context-osint-mcp https://context.everydaysecurity.ai/api/mcpProxies and orchestrates other MCP servers through one unified interface, sanitizing sensitive data in requests and responses.
Scans MCP configurations and source code to detect exposed secrets, shadow APIs, and code-level vulnerabilities in AI agent tools.
Maps and governs AI attack surfaces in application code by detecting LLM calls, agents, MCP servers, and RAG pipelines locally and offline.
Lets an AI client run penetration-testing tools like Nmap, Nuclei, SQLMap, and ZAP through Docker to automate security assessments.
Evaluates agentic AI applications through prompt injection testing, vulnerability assessment, SBOM generation, and static analysis.
Lets Claude orchestrate 80 penetration testing tools, from recon to reporting, with safety controls and audit logging.
Performs security audits for Supabase and MongoDB to find RLS misconfigurations, exposed keys, and risky functions, providing scored reports with fix SQL.
Provides an OSINT reconnaissance suite that classifies indicators and builds curated search URLs from a catalog of 909 specialized tools.
Performs adversarial security testing on AI agents to detect prompt injection, tool misuse, memory poisoning, and MCP server vulnerabilities.
Lets an AI client run data quality checks, PII scans, profiling and schema learning on local data files.
$claude mcp add truthound -- uvx truthoundProvides change control for AI agents by requiring human approval for risky actions and maintaining a tamper-evident audit record.
Validates AI agent tool-call arguments with Pydantic strict mode, strips ghost arguments, and returns self-healing hints for retries.
Performs comprehensive security analysis and vulnerability scanning for Python projects and GitHub repositories.
$claude mcp add vulnicheck -- docker run -i --rm docker.io/andrasfe/vulnicheck:mainVerifies the cryptographic identity and trust status of autonomous AI agents using signed identity documents and DNS-bound attestations.
An offensive security framework designed to probe AI agents and MCP servers for vulnerabilities like prompt injection and privilege escalation.
Provides a per-agent proxy for MCP tools that enforces resource scoping, credential isolation, and structured audit logging.
A privacy-first multimodal data refinery and security firewall that cleanses untrusted inputs and provides hybrid RAG with offline Vietnamese OCR.
Provides an agentic control layer for IDA Pro 9.x, enabling AI clients to perform reverse engineering, debugging, and binary analysis via MCP or REST API.
Assay provides a deterministic canary-oracle benchmark to evaluate the security and data leakage resistance of MCP servers using frozen task sets.