Security MCP Servers

Local-first MCP gateway for coding agents that redacts detected secrets from file reads and command output before they reach model context.

Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.

Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix.

Cortex integration for observable analysis and automated security responses.

Retrieve live and recorded video from a CCTV recording program (VMS) and control it, such as opening live or playback dialogs for specific…

Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.

Trust, W3C DID identity and EigenTrust reputation for AI agents, with attestations, disputes, sybil detection and IPFS audit anchoring.

TheHive integration for collaborative security incident response and case management.

Credential isolation for AI agents. Inject secrets at the network boundary.

Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.

Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.

The firewall for MCP tool calls. Block, audit, replay with evidence bundles.

Deterministic execution governance gateway and W3C DID security guardrail for AI agent MCP tool calls.

MCP server exposing the MITRE ATT&CK framework via the official MCP Python SDK.

Pre-install npm package checks: static analysis, supply-chain attack detection, vulnerability audits, AI hallucination guard and CycloneDX…

Runtime policy enforcement for AI agents that prevents accidental system damage and unauthorized access, with automatic backups before…

Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.

Governance proxy for MCP servers — policy evaluation, human approval, audit trails.

MCP governance proxy with capability tokens, tiered approvals, fail-closed execution and tamper-evident audit receipts, plus preflight…

Query the NIST National Vulnerability Database (NVD) API.

Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning

[glama](https://glama.ai/mcp/servers/@loglux/auth-mcp-gateway) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Auth proxy for MCP servers: OAuth2 with DCR, JWT, RBAC, rate…

Protected RAG storage — agents discover public metadata, content only by access token.

Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

OPNsense firewall operations via API: query ARP, DHCP, firewall rules, logs, interfaces, system status and packet captures.

Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.

Verify AI agent communication with session types and formal proofs

Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

Reverse engineering and security analysis of .NET and native binaries: decompile, compare, patch.

HTTP MCP Server for comprehensive Python vulnerability scanning and security analysis.

APK reverse engineering workspace that orchestrates jadx, apktool, adb and Frida through a workflow engine, on Termux (Android) or PC.

Secrets manager that injects credentials into commands as environment variables so agents never see plaintext secrets, and sanitizes…

AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.

Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.

Zitadel identity management: manage users, projects, OIDC apps, roles and service accounts in natural language.

Scan, protect, and monitor APIs from AI coding tools. Device-level rate limiting.

Local privacy testing for AI agents: scan code for PII and secrets, score execution traces across internal channels, redact text, and…

Unified threat intel - OTX, AbuseIPDB, GreyNoise, abuse.ch, Feodo Tracker

Official BunkerWeb WAF integration to manage services, instances, IP bans, configurations, plugins, and scheduler jobs over stdio or…

MCP server for IDA Pro: decompiler, disassembler, and analysis tools for MCP clients.

Read-only attack-path tools: reachable routes to sensitive assets, and what a fix would cut.

Supply chain risk scoring for npm, PyPI, Cargo, and Go. 9 tools. Behavioral signals.

Thales CipherTrust Manager integration for key management, cryptographic operations and compliance monitoring.

AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.

MCP for Sonatype Nexus Repository Manager and Sonatype Repository Firewall. Manage your DevSecOps practices through AI-assisted Workflows.

Keep patient identifiers out of AI agent context — a local privacy boundary for healthcare agents.

Author, validate, debug, and explain OPA Rego policies through any MCP-compatible client.

Transparent proxy that intercepts, signs, rate-limits, redacts and audits MCP tool calls without modifying client or server.

Stateless zero-knowledge trust gateway and WebMCP shield for AI agents on Midnight.

Detect fake-recruiter and job-offer scams using free OSINT. No API keys.

Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.

Query the RAD Security API for Kubernetes and cloud security findings, reports and runtime data.

Enforces rules from existing agent instruction files (CLAUDE.md, .cursorrules) by blocking prohibited tool calls and logging per-rule…

URL scanning and phishing triage: capture DOM snapshots, network requests and screenshots, and hunt historical scans with a custom query…

Search the Russian software registry for import-substitution and FSTEC/FSB-certified products, with full-text search and manufacturer…

Deterministic security layer your AI can't be. 654 rules, 39 tools, CLI + doctor + host audit.

Zero-knowledge password manager and MCP credential gateway: policy-gated agent access, deterministic passwords, BIP-39 recovery and a…

Pin MCP tool contracts by sha-256; catch silent drift, rug pulls and bait-and-switch in CI.