Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Mund — MCP Security Scanner
MCP serversScan for prompt injection, secrets, PII, and vet MCP servers before installation
@weave_protocol/mund@0.1.12 -
agentforge
MCP serversSafety checks for AI agents: preflight before signing, prompt-injection scan, sanctions, rug checks.
-
CanaryGuard 402
MCP serversDeterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
-
MCP Fortress
MCP serversSecurity scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
-
tech-risk
MCP serversMCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
greyridge-x402-tools@0.8.3 -
agent-security-scanner-mcp
MCP serversSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
agent-security-scanner-mcp@2.0.1 -
mcp-server-security-scanner
MCP serversScan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
mcp-server-security-scanner@1.1.4 -
Agent Safe
MCP serversEmail safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
-
Patronus Security
MCP serversScan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
-
InjectScan
MCP serversScan text for prompt injection: risk score, verdict, matched spans. Built by Crypto Money Maker
-
AgentSafe
MCP serversScan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
-
AgentUnmask
MCP serversScan a URL before your agent reads it: hidden prompt injection, phishing, clean markdown.
-
Heisto
MCP serversPrompt-injection Guard checks and public AI red-teaming arena data from Heisto on Solana.
-
email-guard-mcp
MCP serversEmail safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
email-guard-mcp@1.3.0 -
Koma Gate MCP
MCP serversClassifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
koma-gate-mcp@0.1.1 -
agentglass
MCP serversScan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
-
SmuggleCheck
MCP serversFind hidden prompt-injection text: ASCII smuggling, zero-width/emoji stego, bidi, homoglyphs.
-
Exepal
MCP serversSafety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
-
Web Extract MCP Server
MCP serversPage change monitoring, sitemap discovery, prompt-injection screening, clean markdown. Free preview.
-
kyde score
MCP serversAgent observability via OpenTelemetry: drift, loop and hijack alerts, e.g. after a prompt injection.
-
cc-audit
MCP serversAI-free static security scanner for Claude Code artifacts (Skills, Hooks, MCP configs). Detects data exfiltration, prompt injection, and supply chain risks with deterministic, reproducible results.
git clone https://github.com/ryo-ebata/cc-audit.git -
PromptScan
MCP serversPrompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
qorami
MCP serversCheck an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
qorami-mcp@1.0.0 -
Lovec
MCP serversPrompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
lovec-mcp@0.1.2
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.