Security & Monitoring MCP Servers
Security, identity, secrets, compliance, testing, logs, monitoring, alerts, and observability.
MIMIR
Published by GitHub account abderahmane-ai
MIMIR is a local, non-generative decision server that lets an assistant make typed, calibrated and auditable choices, verifications, rankings and ratings over a
SatGate – Economic Firewall for AI Agents
Published by GitHub account SatGate-io
SatGate governs AI agent API and MCP tool calls with budgets, payment policies and signed receipts for every allow or deny.
OPC UA NodeSet Gate
Published by GitHub account ChanghuLiu
Compares two OPC UA NodeSet2 XML revisions and returns a deterministic compatibility report before a release.
Vulnerability Scanner
Published by GitHub account 4hmetuyar
A local MCP server that lets an assistant start GuardBee security scans on URLs, check scan status, list findings and get remediation guidance.
Vector Store Scanner
Published by GitHub account 4hmetuyar
Probes vector-database endpoints for unauthenticated exposure, letting an assistant check whether embeddings and RAG data are readable without credentials.
Unbounded Consumption Auditor
Published by GitHub account 4hmetuyar
Scans LLM and agent source code for unbounded-consumption or "denial of wallet" risks such as missing token limits, timeouts, loop caps and rate limits.
Tool Poisoning Scanner
Published by GitHub account 4hmetuyar
Scans MCP server source code for tool poisoning in tool descriptions and for confused-deputy tools whose handlers exceed their read-only names.
Ssl Inspector
Published by GitHub account 4hmetuyar
Local MCP server that inspects TLS certificates, cipher suites, protocols and HSTS for domains, so an assistant can audit SSL/TLS configuration.
Slopsquat Scanner
Published by GitHub account 4hmetuyar
Local MCP server that checks a project's declared npm and PyPI dependencies against the live registries to flag slopsquatted or hallucinated package names.
Security Suite
Published by GitHub account 4hmetuyar
A local MCP server bundling secret scanning, dependency CVE auditing, TLS inspection, and DNS/SPF/DMARC checks for code and domains.
Security Proxy
Published by GitHub account 4hmetuyar
A local proxy that sits in front of other MCP servers to block prompt injection, mask PII, enforce policy rules and write a hash-chained audit log.
Secret Scanner
Published by GitHub account 4hmetuyar
Local MCP server that scans files, directories, git history and agent transcripts for leaked API keys, tokens and passwords, with redacted results.
Rug Pull Detector
Published by GitHub account 4hmetuyar
Local MCP client that baselines another MCP server's tool definitions and flags later changes, catching rug pulls after approval.
Prompt Leak Scanner
Published by GitHub account 4hmetuyar
A local MCP server that scans outbound LLM prompts for leaked credentials and PII, with optional redaction or blocking through a reverse proxy.
Prompt Injection Scanner
Published by GitHub account 4hmetuyar
Local MCP server that scans RAG chunks, scraped pages and documents for indirect prompt injection before an assistant reads them.
Oauth Auditor
Published by GitHub account 4hmetuyar
Scans MCP server authorization code for OAuth 2.1 anti-patterns such as token passthrough, missing audience validation and missing PKCE.
Model Scanner
Published by GitHub account 4hmetuyar
Local MCP server that scans ML model files (PyTorch, pickle, safetensors, Keras, ONNX) for supply-chain risks such as dangerous pickle globals.
Memory Poisoning Scanner
Published by GitHub account 4hmetuyar
Local MCP server that scans agent source code for memory-poisoning patterns where untrusted input reaches persistent memory or is recalled into trusted prompts.
Mcp Server Auditor
Published by GitHub account 4hmetuyar
Local MCP server that statically scans other MCP servers' tool definitions for insecure patterns and reports findings with recommendations.
Mcp Config Auditor
Published by GitHub account 4hmetuyar
Audits local MCP client configs (Cursor, Claude, Windsurf, VS Code) for unpinned packages, secrets, typosquats and risky auto-approve settings.
Llm Redteam
Published by GitHub account 4hmetuyar
Runs canary-based jailbreak, prompt-extraction, and obfuscation probes against a live LLM endpoint you control and reports which guardrails were bypassed.
Dns Intelligence
Published by GitHub account 4hmetuyar
Local MCP server that enumerates DNS records, audits SPF/DMARC/DKIM and DNSSEC/CAA, and finds subdomains vulnerable to takeover.
Dependency Auditor
Published by GitHub account 4hmetuyar
Audits npm, pip and other project dependencies against the OSV vulnerability database, reporting CVEs, malicious releases and fix plans.
Db Gateway
Published by GitHub account 4hmetuyar
Local MCP gateway that sits between an AI assistant and a database, masking PII, enforcing role-based table access, rate limits and audit logging.