Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
jev-judge-mcp
MCP serversTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
git clone https://github.com/PyModel/jev-judge-mcp.git -
mcp-safeguard
MCP serversMCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
mcp-safeguard@0.3.2 -
AI Firewall MCP
MCP serversMulti-agent LLM security layer detecting prompt injection and jailbreaks.
ai-firewall-mcp@1.0.1 -
injectshield
MCP serversPrompt-injection firewall for AI agents — scan untrusted text before LLM calls.
@injectshield/mcp@0.1.4 -
promptrejectormcp
MCP serversSecurity gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
prompt-rejector@1.0.1 -
GuardianShield
MCP serversAI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
guardianshield@1.2.1 -
paysafe
MCP serversPayment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection.
paysafe-x402@1.1.1 -
ToolTrust Scanner
MCP serversScans MCP servers for prompt injection, data exfiltration, and privilege escalation.
tooltrust-mcp@1.0.9 -
agentshield-mcp
MCP serversDetect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
@eigenart/agentshield-mcp@0.1.3 -
Zyrax Guard
MCP serversAudit AI agent configs for prompt injection & rogue MCP servers; vet packages
zyrax-guard@0.13.0 -
MCP-Bastion
MCP serversSecurity middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
mcp-bastion-python@5.1.0 -
Laya Decision Gateway
Public APIsSub-35ms AI gateway for prompt injection defense, support ticket triage & content moderation
-
cloakcheck
MCP serversScan a page for hidden prompt-injection payloads targeting AI agents.
-
kagami
MCP serversDeterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
-
Sentinel Scan
MCP serversMCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.
sentinel-scan-cli@1.4.16 -
Tripwire
MCP serversSecurity gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
tripwire-mcp@0.3.1 -
Trentina
MCP serversSecure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense
mcp-trentina-crunchtools@0.5.0 -
agent-immune
MCP serversAI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
agent-immune@0.2.2 -
mcpm
MCP serversMCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
@getmcpm/cli@0.54.0 -
mcp-server
MCP serversBlock prompt injection, evasive spacing, and obscene content before it reaches your LLM.
@ingressward/mcp-server@1.0.0 -
AIShield Security Scanner
MCP serversScans MCP servers for tool poisoning, prompt injection and supply chain risks.
aishield-mcp-server@4.3.0 -
injectcheck
MCP serversScan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
@reneturcios/injectcheck@0.1.19 -
ctxfw
MCP serversZero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.
ctxfw@4.2.0 -
N0N4 Guardian
MCP serversC2PA sign/verify for AI agents, prompt-injection scanning, and signed M2M custody handoffs.
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.