Security MCP servers

Scan, enumerate, and risk-score every MCP server configured on your machine.

AI agent identity, signed credentials, delegated authority and governance evidence.

Secure MCP server framework with 23 security layers and ML threat detection. Zero deps.

Pull one-time .env links from stubs.talix.app into a project. Returns key names, never values.

Offline, read-only auditing of MCP client configuration files with redacted findings

Manage AdGuard Home through AI assistants

Drive a self-hosted Darkmoon Pro AI pentest instance: start runs, read campaigns and findings.

Finds authorization holes in Next.js + Supabase apps and live Supabase databases. No API key.

Verify signed ALEX Evidence Packages. Fails closed on signature or schema errors.

Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.

Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

Privileged command execution proxy with human approval via pkexec or sudo

Send and read one-time encrypted secrets with local encryption.

Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses

The MCP server index that vets servers, not just lists them. Advisory screen before you install.

MCP server for RoboShadow's Rubicon Platform Data API.

Prompt template drift and structural fingerprint sentinel detecting unauthorized prompt mutations an

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

PII/secret redaction, email checks, sanctions screening and OSV vulnerability lookups for AI agents.

Decode JWTs without verifying, flag risky algorithms and claims, verify HS256 or RS256 with a key.

Inspect Kairon VMs, network policy and VM-edge flows from an agent. Read-only by default.

The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.

Prove a hidden value reached a threshold without revealing the value.

Token safety: honeypot sim, contract powers, rug checks, watch alerts, plain card, paper test.

Breach, SIM swap, infostealer, domain lookalikes, MCP registry risk, prompt-injection detection.

Decide by policy, gate behind a human, verify by read-back, record a hash-chained ledger.

One-call trust check for any domain (A0-A4, verdict, signed) + fact passports; same tools as remote

Deterministic authorization and security guard for AI agent actions with signed receipts.