Skip to main content
NeuronFeed

AI Agent Readiness Leaderboard

Which AI tools actually work with AI-agent workflows? We score every tool on 6 dimensions: MCP endpoint, public API, webhooks, developer docs, SDKs, and auth. Total out of 100. Automated weekly rechecks keep the scores current.

Scored
2668
With MCP
101
Public API
642
OAuth2
133
Avg score
22.9
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #1441 · Sett

    AI agents that build, market and publish mobile games

    10Agent
  2. #1442 · Emergent

    Agentic vibe-coding platform that builds full apps from natural language

    10Agent
  3. #1443 · Genesis Molecular AI

    Generative AI for small-molecule drug discovery

    10Agent
  4. #1444 · Wonder Studios

    AI-native film studio collapsing the time from idea to cinematic screen

    10Agent
  5. #1445 · Lumia Security

    Governance and control for enterprise AI agents

    10Agent
  6. #1446 · Lawhive

    Online legal marketplace with an AI paralegal for consumers and SMEs

    10Agent
  7. #1447 · Evertune

    The marketing platform for brand discovery and visibility in AI search

    10Agent
  8. #1448 · Agentio

    AI-native platform for creator-led advertising on YouTube and Instagram

    10Agent
  9. #1449 · Lucis

    AI-driven preventive health platform analyzing 110+ blood biomarkers

    10Agent
  10. #1450 · Halter

    AI-powered smart collars and virtual fencing for cattle ranches and dairy farms

    10Agent
  11. #1451 · Shinkei Systems

    AI-driven robotics for fresher, longer-lasting, humanely processed seafood

    10Agent
  12. #1452 · ChemLex

    24/7 self-driving lab that runs autonomous chemistry to accelerate drug discovery

    10Agent
  13. #1453 · Enzo Health

    Agentic AI-native EHR connecting referral to reimbursement for home health

    10Agent
  14. #1454 · Axiomatic AI

    Intelligence infrastructure for verified science and engineering

    10Agent
  15. #1455 · Icon

    The AI admaker for winning UGC video ads

    10Agent
  16. #1456 · DOJO AI

    The agentic marketing operating system for challenger brands

    10Agent
  17. #1457 · Status

    A gamified AI social world where you play any character in any universe

    10Agent
  18. #1458 · Numa

    AI agents that answer every call and fill the service bay for dealerships

    10Agent
  19. #1459 · Apex Space

    Productized satellite buses manufactured at scale

    10Agent
  20. #1460 · Tenzai

    AI-powered penetration testing platform that runs full, end-to-end pentests autonomously

    10Agent
  21. #1461 · Geordie

    Agent-native security and governance platform that gives enterprises control over their AI

    10Agent
  22. #1462 · Mimic Robotics

    Zurich-based, ETH spin-off building physical-AI systems that learn dexterous manipulation from

    10Agent
  23. #1463 · Pathos AI

    Patient-centric, AI-powered drug development company focused on accelerating cancer therapies

    10Agent
  24. #1464 · Sema4.ai

    Offers a full-stack enterprise AI agent platform for automating mission-critical knowledge

    10Agent

FAQ

›What is MCP?

Model Context Protocol — a standard introduced by Anthropic for AI agents to call external tools. Tools that ship MCP endpoints can be used by Claude, ChatGPT Desktop, Cursor, and others without custom plumbing.

›How is the agent-readiness score calculated?

Each tool gets 0-100 across 6 dimensions: public API (30pt), MCP server (25pt), webhooks (15pt), OAuth/delegated auth (10pt), machine-readable docs (10pt), and official SDKs (10pt). Score is the weighted sum, rechecked as profiles are re-enriched. Full reference: /docs/agent-readiness.

›How often are tools rechecked?

Daily for new tools, weekly for the existing leaderboard. Drift in MCP/API surface area is flagged for editorial review before the score updates.

›What counts as agent-ready?

We consider a tool agent-ready if it has at least 3 of: MCP endpoint, public API, webhooks, OAuth2, an SDK, and good docs. Score 60+ generally means an agent can integrate without source-code-level access.

›Why are some tools missing?

We score every published startup in the directory. Stealth-mode and pre-launch tools aren’t scored until they ship a public product.