Security MCP servers

Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.

Read-only host activity, history, anomalies and evidence from a Vytrix collector.

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

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

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

Zero-knowledge MCP secrets vault for AI agents: secrets injected at runtime, never seen by the model

Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.

Trust metadata for AI agents — check files before building on them, stamp verified work.

Cryptographic spatial proof-of-presence for AV fleets, logistics, AR. 91% spoof detection.

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.

Outcome-first x402 services led by AveDaris Company Intelligence with free task routing on Base.

Deterministic SAST/SCA findings + fix guidance for your AI agent. Runs locally, no account needed.

Discover x402 endpoints and check their trust score before your agent pays them.

Was this document edited, did its redactions hold, is it safe for a model to read — Tamperlens API.

Base crypto safety for agents: honeypot/tax test, address poisoning, rug feed, creator record.

Pre-sign wallet safety: tx simulation, signature decoding, address risk, ABI, URL phishing.

CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.

Is this website a scam? Dated, sourced fraud assessments of domains. Free, read-only, no key.

An MCP server whose confirmation cannot be replayed against a different call.

AI helper for choosing and speccing network & security products from Cisco, Arista, Juniper and more

Look up any domain, IP address or AS number: hosting, DNS, registration, email, TLS and headers.

Send a file to a person as a one-time, encrypted, auto-deleting download link.

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

Run Sherlock, Maigret, Holehe, GHunt, theHarvester, SpiderFoot and more OSINT tools locally

Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.

Plain-English website security check for agents: certificate, headers, scripts, forms, spam.

Local-first Base64, Luhn, key-component XOR, and synthetic ISO-0 PIN block tools.