Security MCP servers

Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.

Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.

Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

HTTP MCP gateway: principal on tools/call + SSE, allowlists, vault rotate, CHP gates.

Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE.

Cryptographic audit trail for Claude Code workflows — tamper-proof timestamps, IETF TTTPS compliant.

Audit Make.com blueprints before importing: hardcoded secrets, dangling refs, risky settings.

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.

Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.

Code security scanner for AI agents. 45+ vulnerability patterns, AST analysis, Solana micropayments.

Verify, discover, and rate AI agents before transacting.

Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

Contextual blast-radius scoring for shell commands an AI agent is about to run

Tells you what leaked in a .har capture, who's on the page, and what to strip. No network calls.

Credential isolation for AI agents. Inject secrets at the network boundary.

Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

Threadlinqs threat-intelligence MCP — 73 tools: threats, detections, IOCs, actors, C2, MITRE, CVEs

Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes

Neutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.

Agent-first E2EE file transfer over MCP: move files between machines in one tool call, gone in 24h.

Verify an AI agent's payment authority: signed mandates, allowlists, and tamper-proof receipts.

OSINT sweep of a digital footprint: breaches, accounts, data brokers, domains and IPs