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. #1729 · NVision

    Quantum-enhanced MRI that images disease metabolism in real time

    10Agent
  2. #1730 · Upheal

    AI-native EHR and clinical notes for mental health therapists

    10Agent
  3. #1731 · The Path

    Outcome-focused AI therapy built by neuroscientists and Calm alumni

    10Agent
  4. #1732 · Crabi

    AI-driven digital auto insurance for Mexico

    10Agent
  5. #1733 · Aracor AI

    AI contract analysis and due diligence for dealmakers

    10Agent
  6. #1734 · Grasp

    Multi-agent AI analyst for finance and consulting workflows

    10Agent
  7. #1735 · Kodesage

    On-premise AI that modernizes legacy enterprise software like COBOL and Oracle Forms

    10Agent
  8. #1736 · Littlebird

    Full-context AI assistant that understands your screen and meetings

    10Agent
  9. #1737 · Hint

    Proactive AI home manager that catches issues before they become problems

    10Agent
  10. #1738 · Bitmagic

    Create playable 3D games from text prompts in your browser

    10Agent
  11. #1739 · Rosebud AI

    Make 3D games and worlds with vibe coding and natural language

    10Agent
  12. #1740 · Comp

    AI-native HR platform for compensation, recruiting and performance

    10Agent
  13. #1741 · ValueBase

    AI assessor intelligence for property tax valuation and appraisal

    10Agent
  14. #1742 · Foundational

    Code-aware data quality and lineage for AI-ready data

    10Agent
  15. #1743 · Verley

    Precision-fermented, animal-free whey protein powered by AI bioprocess design

    10Agent
  16. #1744 · Iridius

    Compliance-by-design AI that turns regulations into code for regulated enterprises.

    10Agent
  17. #1745 · Living Models

    AI foundation models for biology, starting with plant genomics

    10Agent
  18. #1746 · Sympower

    Demand flexibility and storage optimization for Europe's grid

    10Agent
  19. #1747 · Flint

    AI-native personalized learning platform built for K-12 schools

    10Agent
  20. #1748 · Yoodli

    AI roleplay and communication coaching for experiential learning

    10Agent
  21. #1749 · Careforce

    AI workers that find, call, and schedule more patients for healthcare orgs

    10Agent
  22. #1750 · Spacely AI

    Generative AI rendering and staging for architects and interior designers

    10Agent
  23. #1751 · Pinpoint

    The AI social operating system that turns followers into customers

    10Agent
  24. #1752 · Munch

    AI that turns long videos into viral short clips

    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.