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

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #1513 · Slingshot AI

    Foundation model and AI app for mental health

    10Agent
  2. #1514 · Nevis

    Unified AI platform that automates back-office workflows for RIAs and wealth advisors.

    10Agent
  3. #1515 · Basis

    Autonomous AI agents built for accountants

    10Agent
  4. #1516 · AI Proteins

    Designing a new class of de novo miniprotein medicines with AI

    10Agent
  5. #1517 · Valerie Health

    AI front office for independent doctors' practices

    10Agent
  6. #1518 · Alex

    Autonomous AI recruiter that interviews and screens job applicants

    10Agent
  7. #1519 · Orchard Robotics

    AI-powered farm vision that tracks the health and yield of millions of plants

    10Agent
  8. #1520 · Lumai

    3D optical computing that slashes the cost and power of AI inference.

    10Agent
  9. #1521 · CyberRidge

    Photonic encryption that hides data as optical noise, quantum-resistant by design

    10Agent
  10. #1522 · GovWell

    AI operating system for local government permitting and licensing

    10Agent
  11. #1523 · Perceptic

    The AI operating system for pharmaceutical drug development

    10Agent
  12. #1524 · Tucuvi

    Clinically validated AI voice agent for autonomous patient follow-up

    10Agent
  13. #1525 · Morphle Labs

    Automated digital pathology hardware and AI for cancer diagnostics

    10Agent
  14. #1526 · Hook

    AI-driven social app to legally remix and mash up your favorite songs

    10Agent
  15. #1527 · Polaron

    The intelligence layer for materials science and microstructure analysis

    10Agent
  16. Bullfrog turns standard weapons into AI counter-drone gun systems

    10Agent
  17. #1529 · Trent AI

    Layered, context-driven security for the agentic age

    10Agent
  18. #1530 · Paxton AI

    AI legal assistant for research, drafting and document analysis

    10Agent
  19. #1531 · Greenlite AI

    AI workforce automating KYC, AML and sanctions compliance

    10Agent
  20. #1532 · Qeen.ai

    Autonomous AI agents that run content, marketing and conversational sales for ecommerce brands

    10Agent
  21. #1533 · Samaya AI

    Expert AI agents that automate research for investment professionals

    10Agent
  22. #1534 · Farsight

    AI that builds complete pitch books, models and memos for dealmakers

    10Agent
  23. #1535 · Arya

    AI relationship concierge that coaches couples right inside their text messages

    10Agent
  24. #1536 · Origin Lab

    Turning video game worlds into licensed training data for AI

    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.