Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
presign-guard
MCP serversSafe to sign? EVM/Solana/XRPL/Algorand/Stellar txs, permits, tokens; OFAC screen: green/orange/red
-
elthio-mcp
MCP serversSupplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
-
FMCSA Carrier Intelligence
MCP serversUS carrier vetting on FMCSA data: authority, insurance, safety, identity links. Pay per call (x402)
-
rugcheck-ai
MCP serversSolana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
-
Data Compliance Classifier MCP
MCP serversClassify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.
data-compliance-mcp@1.0.25 -
Agent Readiness Auditor
MCP serversAudits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
agent-readiness-auditor@0.5.0 -
voyager-repo
MCP serversAn AI agent's safe read-only scout to orient in an unknown repository before touching it.
@dir-ai/voyager-repo@0.7.0 -
Sanctuary
MCP serversScripture prayers and a safe house-church finder for people who left church but kept the faith.
-
gpsr-listing-lint
MCP serversAudits a product feed row by row against Article 19 of the EU General Product Safety Regulation
@readystack/gpsr-listing-lint@1.0.2 -
K8s MCP Server (Go)
MCP serversSafe Kubernetes access for AI agents via MCP. Read-only by default, with explicit permission modes.
https://github.com/kaneg/k8s-mcp-go/releases/download/v0.4.6/k8s-mcp-go_0.4.6_darwin_amd64.mcpb -
universalbench
MCP serversRun code, query databases, call any LLM, and commit to GitHub from your AI, safely. Free tier.
-
vouch
MCP serversCheck if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.
-
presidio-hardened-x402-mcp
MCP serversPre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.
presidio-hardened-x402-mcp@0.4.0 -
NeuroDock Task Fractionator
MCP serversDecompose a vague goal into atomic 5-90 minute tasks and surface the next safe action.
neurodock-mcp-task-fractionator@0.1.0 -
Woo Revenue Incident Graph
MCP serversCheck WooCommerce checkout-change risk using public evidence and privacy-safe store signals.
-
mcp-regulated-ai-compliance
MCP serversRegulated-industry AI compliance: EU AI Act, APRA, NIST AI RMF, ISO 42001, AU AI Safety.
@hellouchit/mcp-regulated-ai-compliance@0.2.3 -
Bird MCP by usefulapi
MCP serversRead SMS, WhatsApp, email, contacts and audiences from your Bird workspace, plus safe CRM writes.
-
Increase MCP by usefulapi
MCP serversRead-only Increase banking observability plus one safe non-money-moving write, for AI agents.
-
Lorg Check
MCP serversIs this token a trap? Is this address safe to pay? Signed verdicts on Base and Ethereum.
-
Bicycle routes generator MCP
MCP serversMTB and road cycling routes on real OpenStreetMap trails, saved as GPX with safety warnings.
https://github.com/Marc-Armillas/bicycle-routes-generator-mcp/releases/download/v0.5.0/bicycle-routes-generator-mcp.mcpb -
walkaround
MCP serversLaunch check for AI-built apps: SAFE or DO NOT SHIP verdict, with evidence and paste-back fixes.
-
BliniBot Agent Lounge
MCP serversA safe place where AI agents meet, build, sell services, invite agents and bring real people.
-
apiwatch
MCP serversIs this model or API still safe to call? Retirement and breaking change dates, with the fix.
-
TokenGuard
MCP serversSolana rug check before you buy: SAFE/CAUTION/DANGER from chain state. Free key or x402.
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.