Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
pgmoat
MCP serversGoverned, read-only Postgres access for AI agents: SQL safety, RLS, budgets, tamper-evident audit.
pgmoat@0.1.2 -
Exepal
MCP serversSafety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
-
AgentFuel
MCP serversSafety checks for trading bots: Solana and Robinhood Chain rug-checks, launch feed, safe_buy.
-
Safety-first Database Guardrail & Sandboxing MCP Server for AI Coding Agents
@ritualdev-lab/dbshield@0.2.1 -
WebLens
MCP serversWeb pages as clean data, plus RugProbe Base token safety checks. Pay per call in USDC (x402).
x402-weblens-mcp@1.4.0 -
Flockward
MCP serversFree safety checks for AI agents: links, sites, MCP servers, and pages read with traps removed.
-
akari-x402
MCP serversAkari x402 tools: funding-edge + token-safety previews, service list, paid 402 call helper.
-
cerulion
Agents & frameworksCerulion (YC S24) gives AI agents a harness to control real robots. Our open-source runtime and harness give any AI agent a physical body, inside safety limits the robot enforces, and tools to autonomously debug recorded robot failures. It's ROS 2 compatible.
git clone https://github.com/cerulion-inc/cerulion.git -
Upgrade X-Ray: npm & PyPI dependency update diff
MCP serversDiff two npm/PyPI versions or lockfiles: new install scripts, network/shell/eval calls, new deps.
-
awesome-llm-observability
Skills50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
GroundTruth - Environmental Records
MCP serversFederal environmental records near any US location, with dates and provenance; never a safety score.
-
CarrierScrub
MCP serversCheck a US motor carrier's FMCSA authority, insurance and safety record: a dated GO/CAUTION/STOP.
-
freight-intel
MCP serversFreight carrier intel: new FMCSA authority feed, carrier lookup by DOT/MC, safety screen (CSA/SMS).
-
GadgetHumans API Hub
MCP servers236 MCP tools free (rate-limited): token safety, OCR, DNS, 228 x402 routes. No key.
-
Oveyon Mail
MCP serversEmail for AI agents: send, receive with a safety verdict, reply and approve, as MCP tools.
-
StalkChain Data
MCP serversCrypto research: what FOMO's top traders buy, real wallets and PnL, token safety, smart money.
-
obol
MCP serversPre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402.
-
solidus
MCP serversSolana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight.
-
mcp-server
MCP serversPay-per-call AI + web + on-chain tools over x402 (USDC on Base): LLM, SEO, extract, token safety.
@true402.dev/mcp-server@1.3.2 -
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 -
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 -
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 -
Hawaii Conditions MCP Server
MCP serversReal-time surf, weather, trail status, volcano, ocean safety, and restaurants for Hawaii.
-
KarmaDue
MCP serversPre-install safety check for agents: known traps, tested fixes, malware reports. No account.
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.