Official VirusTotal MCP server: threat reports, file and URL submissions, and analysis recovery.
Showing 49–96 of 1,661
Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Sub-ms PreToolUse firewall, feedback memory, and single-use permits for AI coding agents.
AI-writing detection (EN/ES) that shows the evidence: named tells, hidden characters, citations.
Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.
AynOps is a reconnaissance focused MCP Server which gives reconnaissance capabilities to AI Clients
Security scanner for AI Agent skills, plugins, and MCP servers with A-F grading.
Sign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.
Answer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.
Security testing MCP server for penetration testing, forensics, and vulnerability assessment
Scans AI-written code for leaked secrets, unguarded routes and missing RLS.
Query 47 EU regulations (GDPR, NIS2, DORA, AI Act) - 2,438 articles, 3,712 recitals, ISO 27001
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
MCP server for 1Password service accounts — tools and resources for vaults and credentials
Runtime proxy for MCP security, cost governance & audit
Local-first paper integrity checks: hallucinated citations, AI-text, plagiarism, venue guidelines.
Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
Microsoft 365 administration via Graph API application permissions (read-only by default).
MCP server for Cyberbro IOC extraction, enrichment and reputation analysis.
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Permission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.
Microsoft Dataverse MCP server: CRUD, FetchXML, metadata, schema, audit, batch and security roles.
Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix.
Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.
Query FedRAMP 20x KSIs, NIST controls, and compliance docs via 20 MCP tools.
Credential isolation for AI agents. Inject secrets at the network boundary.
Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
Policy-enforcing MCP proxy with portable evidence output.
4,685 pre-production checks: security, performance, scale, integrations, post-launch, people.
Manage Authentik through AI assistants
Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.
Accountable autonomy proxy: gating, tamper-evident audit, time anchor for every action
Accountable autonomy MCP server: gating, tamper-evident audit for every action
VulnCheck exploit intelligence — CVE research, exploit data, advisories, and threat analysis.
Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.
Zero-dependency Web Crypto & AI Agent MCP Server (AES-256-GCM, RSA-4096, PQC, Signatures).
Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense
Local credential broker: agents call APIs, SSH and DBs via scoped presets; secrets stay in keychain.
Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
