- AIShield Security Scanner @lm203688/aishieldScans MCP servers for tool poisoning, prompt injection and supply chain risks.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Raven Nest @tidynest/raven-nest-mcpAI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints25% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- MCPAmpel - MCP Security Scanner @diemoeve/mcpampelScan installed MCP servers for security vulnerabilities with 16 detection engines.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Bawbel Scanner @bawbel/bawbel-mcpScan MCP servers and skill files for AVE vulnerabilities. Conformance scoring and threat intel.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Android Security Analyzer @ako2345/android-security-analyzerMCP server for static security analysis of Android source code4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- Audit Gap Auditor @guardbee/audit-gap-auditorOWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Context Oversharing Auditor @guardbee/context-oversharing-auditorOWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Deepsleuth @deepsleuth/deepsleuthDeterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- A2A Auditor @4hmetuyar/a2a-auditorScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agent Graph Auditor @4hmetuyar/agent-graph-auditorFinds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Dechonet @node-man/dechonet-mcp13 security recon tools for AI agents — DNS, SSL, HTTP, email, ports, ASN. Health Score 0-100.20% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Jikida.io MCP @jikida/mcpSecurity tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- SecHelix @omarmohelal/sechelixEvidence-first security review of authorized repositories. Read-only, root-confined, no shell.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Sentinel Scan @ventrova/sentinel-scan-cliMCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- BeVigil OSINT @santhosh-005/bevigilDiscover mobile app attack surfaces via BeVigil OSINT — hosts, subdomains, URLs, and more.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MCPSentinel @gentaarnezzi/mcpsentinelPrecision-first security scanning for Model Context Protocol servers.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- GAUNTLEX @sanjoy1234/gauntlexConcurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Cybersec @xu-c0/cybersec-mcpCybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- WhisperGraph @whisper-sec/whisper-graphThe internet's infrastructure graph for AI agents - 46B nodes and edges, free trial via 2 HTTP calls13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Eidolon @sudohnim/eidolonPrivacy-first OSINT scanner: breaches, credentials, Shodan, username sweep. Scored PDF report.23% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Arcwall Security @rom-baro/arcwall-securitySecurity scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- OSINT MCP @rjn32s/osint-mcp26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run.22% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- DechoNet MCP @dechonet/mcp25 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Recon Kit @nan786521/recon-kit-mcpRead-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
