Security MCP servers

Scan a website for SEO, accessibility, performance and security issues, and read the report.

Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted

Solana token safety and pump.fun rug checks: free for any mint, paid depth in USDC on Solana or Base

Query devices, alerts, syslog, Suricata IDS, NetFlow and captures on your Netmon appliance.

Large files and secrets between people and agents, never through the chat or the model.

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

Disposable email inboxes for AI agents — OTPs and magic links auto-extracted. No signup to try.

Check an MCP server, skill or plugin before your agent uses it: tool text on record, changes graded.

Install and run open-source OSINT tools in a local sandbox, asking before runs that touch a target.

Local crypto inventory for developers and AI agents; coverage and limits inside the CBOM.

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

Sign and register statements on a Forestrie log, verify receipts, buy grants via x402 within caps

Fetch a SCITT receipt, its genesis and on-chain accumulator for @forestrie/mcp-verify to verify

Verify a SCITT receipt under a trust root you hold — offline, no backend, no key, no network

Request and send secrets for AI agents, end-to-end encrypted and never shown in the chat.

Private, programmable networking for the AI age: manage networks, devices, hubs and VPN.

Anonymize drawing PDFs: mask names, logos, addresses, emails; flattened PDF or expiring link.

Evaluate an MCP server with passmcp and verify its attestations, from inside the agent. Read-only.

Public IP signals (cloud hosting, Tor exits) and Maskbreak API status for fraud checks.

Verify an npm or PyPI package before install: advisories, install scripts, typosquats, repository.

Grade a URL as an attacker and a customer would see it; scan a repo; check Supabase, Stripe, Vercel.

Check if your exit IP works for ChatGPT, Claude, Gemini: ASN, proxy/IDC type, risk, AI availability

Role-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.

Send and read end-to-end encrypted documents. Your private key never leaves your machine.

Check whether a URL or IP is safe before an AI agent fetches or opens it.

ScriptProbe: Check npm install scripts and publisher changes before installing.

A record of what an agent did that the agent cannot quietly rewrite, and a way for anyone to check.

Safe, self-hosted ZAP operator for guided AI security scans and reports.