Security MCP servers

Local execution gate: fixed deadlines, operator-only controls, read-only setup and readable denials.

Verify PDF signatures, detect tampering, and identify PDF/A and PAdES conformance levels.

Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.

Share agent skills across your team, scan them for risk, and track what's actually used.

Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.

Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

Invisible per-recipient image watermarks. Mark one copy per recipient, then identify a leaked copy.

IP intelligence lookups and FindIP Shield visitor risk signals for AI assistants.

Post-quantum (ML-DSA-65/Dilithium-3) proof, provenance & AI-decision receipts, paid via x402.

Post-quantum (ML-DSA-65/FIPS-204) agent identity + AI-decision receipts, verifiable offline.

Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +23. Local. Deterministic.

Tailscale MCP server for managing your tailnet from AI assistants

Offline secret scanning for AI agents. Redacted findings; scans text and files in a chosen root.

Keychain-backed secret broker: an AI agent can use your keys, but no tool ever returns one.

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

AI Security Harness: SAST, secrets, deps, containers, config & OWASP LLM. Scans locally.

Hosts, metrics, Docker and authorized_keys over a macOS terminal's live SSH connections

Scan what an AI agent running as you can reach; optionally verify which keys are live (x402).

Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.

The cryptography a JavaScript or TypeScript codebase uses, and which a quantum computer would break.

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks.

Check products, credentials, claims, and agents against NPC Labs verification records.

Check if an MCP server's tool definitions changed after approval, from a signed public log.

Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

A security-focused MCP server for self-hosted n8n Community Edition.