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
2662
With MCP
80
Public API
646
OAuth2
148
Avg score
23
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #1513 · FINNY AI

    AI prospecting and marketing engine that helps financial advisors find and win clients

    10Agent
  2. #1514 · CuspAI

    AI foundation models that act as a search engine for new materials.

    10Agent
  3. #1515 · Traversal

    The AI SRE agent that finds root causes in complex production systems

    10Agent
  4. #1516 · Epirus

    High-power microwave systems that disable drone swarms in flight

    10Agent
  5. #1517 · Phia

    AI personal shopping assistant that compares prices and resale value across thousands of brands

    10Agent
  6. #1518 · Avantos

    AI operating system for wealth and financial services firms

    10Agent
  7. #1519 · Corgi

    AI-native business insurance platform for startups

    10Agent
  8. #1520 · David AI

    The data layer for next-generation audio and voice AI models

    10Agent
  9. #1521 · Lindus Health

    The anti-CRO running radically faster, AI-enabled clinical trials end to end

    10Agent
  10. #1522 · Genesis AI

    Universal robotics foundation model for general-purpose physical AI

    10Agent
  11. #1523 · Edison Scientific

    AI scientist that compresses months of research into a single day

    10Agent
  12. #1524 · Foundation

    Full-stack general-purpose humanoid robots with proprietary actuators

    10Agent
  13. #1525 · Eridu

    Rebuilding the AI data center network to break the interconnect wall

    10Agent
  14. #1526 · Olix Computing

    Photonic AI inference chips that skip the need for HBM

    10Agent
  15. #1527 · Adept AI

    AI that takes actions in any software

    10Agent
    API
  16. #1528 · Poolside

    AI platform for software engineering

    10Agent
    API
  17. #1529 · micro1

    Human intelligence infrastructure for high-quality AI training data

    10Agent
  18. #1530 · Video Rebirth

    Industrial-grade generative video engine (BACH) for professional, cinematic film creation

    10Agent
  19. #1531 · Ciroos

    Multi-domain AI SRE teammate that automates and augments operations and incident response

    10Agent
  20. #1532 · General Intuition

    Frontier lab training spatial-temporal AI agents on video game clips

    10Agent
  21. #1533 · ThinkLabs AI

    Physics-informed AI that keeps power grids reliable amid surging AI demand

    10Agent
  22. #1534 · Bioptimus

    Building the first universal AI foundation model for biology.

    10Agent
  23. #1535 · PhysicsX

    AI-native engineering simulation that optimizes physical products in minutes.

    10Agent
  24. #1536 · XBuild

    AI construction estimating and proposals in under 15 minutes

    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.