Library
87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Prompt-cache prefix guardian
MCP serversCache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.
-
GuardLayer
MCP serversSecurity checks for Next.js + Supabase apps: code scan, read-only live DB check, fix confirmation.
-
Agent Payment Guard
MCP serversCheck wallets and tokens before an agent pays or trades: sanctions, honeypots, taxes, reputation.
-
Verify agent tool claims against Ed25519 receipts and collapse syndicated RAG copies locally.
epistemic-guard@0.4.2 -
bounty-guard
SkillsZero-dependency Python CLI, GitHub Action, and MCP server scanning untrusted GitHub issues and repositories for prompt injection, CI secret exfiltration, and cryptographic bounty escrow.
git clone https://github.com/doomsday-network/bounty-guard.git -
Local LLM Guard for Ollama / llama.cpp
MCP serversGoverned local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
ai-guardian-aiops@0.14.1 -
presign-guard
MCP serversSafe to sign? EVM/Solana/XRPL/Algorand/Stellar txs, permits, tokens; OFAC screen: green/orange/red
-
OSA Procurement Guard
MCP serversPre-purchase trust, pricing and budget decisions for AI agents buying APIs and MCP tools.
-
Tool Guardian
MCP serversToo many MCP servers eating your context? A router that loads each tool's schema only when needed.
tool-guardian@0.10.1 -
Run Budget Guard
MCP serversHard dollar, token, call and time caps shared by every sub-agent in one agent run.
-
Server and secret guardrails
MCP serversLocal checks for sudo, systemd, sshd, ufw, and secret leaks before an agent applies them.
-
Namespace guard for merged toolboxes
MCP serversPre-connection collision audit for merged MCP toolboxes, trust-graded, with signed routing receipts.
-
x402-presign-guard
MCP serversPre-sign EVM tx/approval safety for AI agents: decode calldata, flag drainers, return GO/HOLD/BLOCK.
x402-presign-guard@0.1.1 -
alalanet guard — check before you install
MCP serversCheck packages, repositories, skills and MCP servers before agents install or connect. Signed.
-
Agent Guardian — MCP Contract Auditor
MCP serversAudit MCP tool contracts and compatibility; includes owned-service HTTP check demos.
-
presign-guard wallet
MCP serversAgent wallet with limits: pays x402/MPP on Base, Solana, Tempo, XRPL and Algorand; phone approval.
presign-guard-wallet-mcp@0.34.0 -
mcp-config-guard
MCP serversReads .mcp.json / .vscode/mcp.json / claude_desktop_config.json while you edit it and marks the line
@readystack/mcp-config-guard@1.0.5 -
payment-guard-mcp
MCP serversPre-send risk check for AI agents that move money — screen an address or payment URL before sending.
payment-guard-mcp@1.3.0 -
prompt-guard-mcp
MCP serversScans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
-
Syl Guardian
MCP serversCausal check on AI agent claims, from ad-spend/ROAS lift to any decision: pass, caution or hold.
-
Pre-execution Base eth_call/eth_estimateGas simulator & ERC-20 approve drain detector.
-
Livestock Counterparty Guard
MCP serversUSDA P&S checks for livestock buyers, dealers, agencies and packers before sale or onboarding.
-
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
tripwire-guard@0.4.2 -
CYRE Guardian
MCP serversSolana address risk grades and token scans for AI agents. Pay-per-call via x402 (USDC on Base).
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.