Google tells you what exists. Faceabot tells you what holds up.
Catches leaked credentials and PII in outbound LLM prompts
Package npm :@guardbee/mcp-prompt-leak-scanner · website · measurements and detailsScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Package pypi :agentvuln · measurements and detailsMCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
Package pypi :mcp-safeguard · website · measurements and detailsAI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
MCP endpoint :https://mcp.skillssafe.com/sse · website · measurements and detailsScan configs, files, or text for leaked secrets and obvious misconfigurations. Nothing stored.
MCP endpoint :https://mcp.knurl.tools/mcp · website · measurements and detailsScans files for leaked secrets and API keys
Package npm :@guardbee/mcp-secret-scanner · website · measurements and detailsScans RAG content/scraped pages for indirect prompt injection
Package npm :@guardbee/mcp-prompt-injection-scanner · website · measurements and detailsOWASP threat scanner auditing codebases for safety leaks.
MCP endpoint :https://codevulnerability-mcp.vercel.app/api/mcp · measurements and detailsSecret scanner preventing leaks of corporate keys and credentials.
MCP endpoint :https://vaultguard-mcp.vercel.app/api/mcp · measurements and detailsScans MCP servers for prompt injection, data exfiltration, and privilege escalation.
Package npm :tooltrust-mcp · website · measurements and detailsScans MCP servers for tool poisoning, prompt injection and supply chain risks.
Package npm :aishield-mcp-server · website · measurements and detailsScan for prompt injection, secrets, PII, and vet MCP servers before installation
Package npm :@weave_protocol/mund · website · measurements and detailsChecks whether a name appears in the ICIJ Offshore Leaks database (offshore structures), for complia
MCP endpoint :https://api.mcp.ai/p_offshore_leaks · website · measurements and detailsScan text and git diffs for committed credentials using real vendor key formats plus entropy.
MCP endpoint :https://secrets-leak-audit-mcp.mcpize.run/mcp · website · measurements and detailsLocal read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
Package npm :tripwire-guard · website · measurements and detailsDeterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
MCP endpoint :https://sigma-gate-864996675261.us-central1.run.app/mcp · website · measurements and detailsStatic AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.
MCP endpoint :https://neon_innovation_lab--mcp-security-auditor.apify.actor/mcp · website · measurements and detailsScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Package npm :@guardbee/mcp-ai-code-scanner · website · measurements and detailsLocal-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
Package npm :husk-sec · website · measurements and detailsSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
Package npm :agent-security-scanner-mcp · website · measurements and detailsAI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Open reliability data · Add Faceabot to your AI · Help · Privacy · Terms