安全 MCP 服务器

Static scanner that checks Claude Code skills, plugins and MCP servers for exfiltration, install hooks and prompt injection before you…

Cryptographic receipts for AI outputs on Base or Solana via x402.

Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

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

Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.

Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).

Zero-trust security proxy, pre-execution blast radius simulation, DLP secret redaction, and cryptographic audit logging for MCP.

AI-native HTTP security testing MCP server — 17 tools with raw HTTP/1.1 + HTTP/2 control

Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.

AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI

Find MCP servers by describing a task and get advisory trust screens before connecting, using the mcpindex directory.

Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.

Verify artifacts produced by AI agents: schema, emptiness, provenance, authority.

Domain security & privacy checker as an MCP server. 17 live checks, 0-100 score, local-first.

Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).

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

JSON risk briefs for wallet addresses, tokens and URLs: scores, flags and sources from phishing, scam and URL-reputation heuristics,…

Etch is a signed audit chain for AI agent decisions, offline-verifiable against pinned public keys.

Enterprise security and code-safety guardrail for AI agents featuring AST taint analysis, SARIF/SBOM generation, and policy gates.

AI-Powered AWS security analysis: scan IAM policies and CloudFormation for risks and escalation.

Policy proxy for MCP tool calls. A denied call never reaches the downstream server.

Check messages, npm packages and crypto addresses before acting. Read-only scanner tools.

Offline security helpers for AI-built (vibe-coded) apps: classify whether a key is safe to expose, generate Supabase RLS audit SQL and…

Check the reputation of AI microservices and public APIs from an open trust registry.

The body an agent asks before it acts: decide, approve, and keep a signed record on your machine.

Read-only AWS audit scanner: public S3 buckets, root and user MFA gaps, unused access keys, world-open security groups, CloudTrail gaps,…

Free U.S. exclusion, debarment and licence screening with a signed receipt of the lists checked.