14 件の#prompt-injection MCP サーバー & クライアント

Community MCP server for Jev-powered claim verification, prompt-injection screening, semantic ranking, and batch classification.

Runtime security oracle for AI agents — scan prompts, tool calls, and outputs before execution. Pay-per-call via x402/USDC, no accounts needed.

Tooltrust Scanner

AgentSafe-AI

Scan MCP servers for security risks before your AI agent trusts them. Detects prompt injection, supply chain attacks (including the LiteLLM 1.82.7/1.82.8 backdoor), excessive permissions, arbitrary code execution, typosquatting, and tool shadowing. Add to your .mcp.json and let y

Pidgeon

Pidgeon

Email inboxes for AI agents. Give an agent its own address in one call; it sends, receives and replies in threads, waits for a sign-up code and gets it back already extracted, and hands a conversation to a person when it

nexus-mcp — jpi-guard & PII Guard

nexus-api-lab

Japanese LLM security APIs — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free to start, no credit card required.

VerityLayer — fail-closed verify-before-you-act trust gate for AI agents. 5 tools: verify_fact, detect_injection, moderate_content, redact_pii, guard_action. Keyless, pay-per-call via x402 (USDC on Base); every verdict ships an Ed25519-signed receipt. Run: npx -y @veritylayer/mcp

Agent Immune

denial-web

Adaptive security toolkit for AI agents. Assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts with role-lock and sandboxing, and monitor metrics — all locally via MCP. Zero false positives on bench

Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.

MCP server providing 9 security intelligence tools for AI agents. Real-time threat detection with pay-per-request USDC micropayments via x402 protocol. Free tier included (3 calls/day, no account needed).

Zentric Protocol

ZentricProtocol

Prompt injection and PII detection MCP server for AI agents. Deterministic, sub-25ms. Returns CLEARED/ANONYMIZED/BLOCKED verdict with matched signatures, PII entities, and GDPR Art.30 audit report. 2,000 free requests/month.

Heimdall — Mcp Security Scanner

caglarbozkurt

Security scanner for MCP servers — vet an MCP before you wire it into an agent. Detects prompt-injection, credential exfiltration (via taint analysis), RCE, and supply-chain risks, and catches cross-server exfil chains no single server reveals. Zero-dependency local CLI, SARIF ou

The first production MCP server with NIST FIPS 204 post-quantum receipts. Every AI agent tool call is policy-gated, hybrid-signed (Ed25519 + ML-DSA-65), and forensically provable — offline, forever. Fail-closed architecture: if the Trust Gate backend is unreachable, every decisio

Scan OpenClaw SKILL.md and MCP tool definition files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks. The only scanner targeting agent skill file formats.

Middlebrick

middleBrick

Scan APIs for security vulnerabilities and get OWASP risk scores. Detects auth bypass, BOLA/IDOR, data exposure, prompt injection, and 12+ security categories.