by Manavarya09 · MCP Server · ★ 156
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is public-apis-live safe to install? View the security audit →
| Stars | 156 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 62/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-22 |
| Created | 2026-06-17 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~26k |
public-apis-live 2901 working public APIs · verified 2026-06-18 · refreshed daily — 🔎 Search · 📊 Benchmark Aggregated from the top public-API lists, deduped, and reachability-checked every day. Only working APIs are listed below; dead/unverified ones are collapsed at the bottom. Try it: · Use it in Claude (plugin) Then ask the agent to pick a working API for any task.
These tools work well together with public-apis-live for enhanced workflows:
Looking for a public-apis-live alternative? If you're comparing public-apis-live with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Free crypto news API - real-time aggregator for Bitcoin, Ethereum, DeFi, Solana & altcoins. No API key require
The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents,
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
A structural code search engine for Al agents.
Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, s
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: