Library
87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
defi-guard-mcp
MCP serversDeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health.
@iniit/defi-guard-mcp@0.2.0 -
firestore-rules-guard
MCP serversAudits firestore.rules and storage.rules for public access, expired test-mode dates and missing owne
@readystack/firestore-rules-guard@1.0.4 -
MCP Security Guard
MCP serversAudit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
mcp-security-guard@0.9.2 -
agentic-wallet-guardian-v3
MCP serversExplainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
agentic-wallet-guardian-mcp@3.1.0 -
Tollary Agent Transaction Guard
MCP serversLocal fit-check and safe integration guidance for non-custodial Base USDC agent transactions.
tollary@0.1.0 -
Context Guardian
MCP servers40 turns: 1,130,722 tokens upstream -> 161,141. A fail-open compaction proxy for local models.
context-guardian@0.16.0 -
TAS Guard
MCP serversOrder limits, phone approvals and a kill switch in front of any broker or exchange MCP server.
tas-guard@0.5.1 -
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 -
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
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.