The real catalog of tools for AI agents

Finds the end-of-life runtimes an AI assistant still writes for you — node:20, python3.9, ubuntu-22

Encyclopedia of Life (EOL) MCP

Is this version still supported? End-of-life dates for 14 runtimes and operating systems.

Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.

Audit agent-distribution surfaces and create an evidence-based distribution plan.

Package alive? Verdict with evidence: deprecated, archived, stale or active; plus runtime EOL dates.

Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

Publisher revenue audit: ads.txt and ad-stack checks, Sulvo onboarding, and Boost ad-block recovery

Scan a public GitHub repo for known Vercel Python-runtime deploy footguns.

Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.

Build, preview, deploy and export academic surveys: blocks, flow logic, experiments, quotas, data.

Reads firebase.json and names the files your next firebase deploy would publish to the open web

Local structured analysis of deployed EVM runtime bytecode

Encyclopedia of Life species data. No key required.

Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.

Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.

AI-native training platform for cyclists and runners: calendar, rides, readiness, sourced science.

Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.

Model inventory and governance: trace deployed models and their dependencies as an append-only log

EOL dates, risk scores, CISA KEV exposure, SBOM audits and edge-device EOS for 500+ products.