Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
AgentWatch
MCP serversRead-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
-
AAAA-Nexus MCP
MCP serversFormally verified AI safety APIs. 75+ endpoints, pay-per-call via USDC x402, no signup.
aaaa-nexus-mcp@0.1.1 -
Nutanix AIops
MCP serversGoverned Nutanix Prism Central v4 ops: clusters/VMs/storage/DR/LCM/RCA, ETag-safe, 51 tools.
nutanix-aiops@0.14.0 -
Divoom LAN Watchface
MCP serversMCP server for Divoom LAN watchface APIs; read-before-write safe. V2 editor linked in README.
mcp-divoom-lan@0.1.1 -
PlainText Wallet Approval Checker
MCP serversExplains wallet approvals and signature requests in plain language: SAFE, CAUTION or RISK.
-
x-mcp-ai
MCP serversSafety-first X (Twitter) API v2 MCP server: 41 typed tools across 12 packages, policy-gated.
x-mcp-ai@0.8.0 -
cli-bridge-mcp
MCP serversOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
cli-bridge-mcp@0.3.0 -
quantaseal
MCP serversQuantum-safe vault, encryption & compliance for AI agents. NIST FIPS 203/204 ML-KEM-768 + ML-DSA-65.
@quantaseal/mcp-server@1.1.3 -
Household Recall Watch
MCP serversHousehold recall checks over public CPSC, openFDA, EMA and EU Safety Gate data. No API key.
https://github.com/MGrin/recall-radar-mcp/releases/download/v0.2.1/household-recall-watch.mcpb -
Open Call Portal
MCP serversSearch PII-free opportunities, availability, and live events; prepare safe no-write form handoffs.
-
deskcert
MCP serversEvaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
deskcert-cli@0.1.5 -
Hawaii Conditions MCP Server
MCP serversReal-time surf, weather, trail status, volcano, ocean safety, and restaurants for Hawaii.
-
gws-admin-mcp
MCP serversSafe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
-
KarmaDue
MCP serversPre-install safety check for agents: known traps, tested fixes, malware reports. No account.
-
dappgrade — onchain app health index
MCP serversPre-transaction health and safety verdicts for onchain apps, by contract address.
-
FreeRDC
MCP serversSafe folder access for ChatGPT and Claude: read, write and search files, risky tools opt-in.
-
voyager-browser
MCP serversVoyager's web-page sense: safe read-only observation of one live URL (structure, security, a11y).
@dir-ai/voyager-browser@0.7.0 -
voyager-net
MCP serversA safe, read-only, authorized audit of one host you own: DNS, ports, TLS, HTTP hygiene.
@dir-ai/voyager-net@0.14.0 -
Trust Check
MCP serversBase crypto safety for agents: honeypot/tax test, address poisoning, rug feed, creator record.
-
Agentic MCP
MCP serversLocal coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.
mcp-agentic-server@1.8.2 -
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 -
mcp-fetch
MCP serversSSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls.
@infoinlet/mcp-fetch@0.1.1 -
idml-mcp
MCP serversMCP server for AI agents to read and safely edit Adobe InDesign IDML files. No InDesign required.
idml-mcp@0.1.1 -
LatAm Fintech Synthetic Data
MCP serversPrivacy-safe synthetic financial data for LatAm fintech, AI agents, testing and ML.
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.