Security servers scan code and dependencies, look up threat intelligence, and query SIEM tools. Hold them to a higher bar: published source, pinned versions, and a clear tool list. 1524 published MCP servers match this ranking. The highest trust scores right now are Nvd at 67, Postcodes at 67, Propublica Nonprofit at 67. The order is the published trust score: registry record, license, maintenance, popularity, documentation, and security signals. Featured slots, when an editor sets them, are labeled and do not change the score. Best security MCP servers is not a paid placement.
Every server that matches this ranking, ordered by trust score.
Turn a prompt and a link into a branded, print-ready QR code that always scans.
by cloudcorprecords · TypeScript
Persistence hook auditor: scan repos for auto-exec hooks, flag Shai-Hulud patterns.
by devinder1 · HTML
Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload.
by cloudcorprecords · TypeScript
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
One verified household record for your AI: accounts, holdings, fees and Score. Can't move money.
Agent tool-call guardrail: fail-closed runtime security verification with Ed25519 evidence receipts.
Dynamic QR codes for AI agents — custom styling, scan tracking, webhooks
by mishrasanjeev · TypeScript
OAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.
by pipeworx-io · JavaScript
eBay MCP — Browse + Taxonomy APIs via client_credentials OAuth
by pipeworx-io · TypeScript
SBIR MCP — wraps the SBIR.gov public API (free, no auth)
Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture
PoC benign MCP server for update-hijack security research
Runtime AI-to-AI security monitor. 23 anomaly types, OWASP MCP Top 10 coverage.
This package is intended for demonstration only. Maintained by JFrog Security.
Moltbook MCP server: post, comment, upvote, DMs, communities. API key auth.
Scans Base L2 smart contracts for security risks. Risk score 0-100, detects backdoors & proxies.
MCP smart contract scanner with NEAR-focused security context.
Minimal MCP server for Ghost Security API - compatible with all MCP clients
Submit URLs to Google and Bing for indexing, scan sitemaps, check index status.
Process management and monitoring for AI agents with strict security boundaries
Real-time semantic security for AI coding agents and MCP tools
Signed, non-replayable API auth. Agents self-register and sign requests with ERC-8128.
SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
Enterprise certification for codebases with multi-agent security, reliability, and quality audits