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. #721 · Klariqo

    Voice AI and signed call records for call centers, running inside VICIdial

    40Agent
    API
  2. #722 · ElevenLabs

    The most realistic AI voices for creators, developers, and enterprise.

    35Agent
    PythonTypeScript +3
  3. #723 · 01.AI

    Founded by Kai-Fu Lee — maker of the Yi model family.

    35Agent
    Python
  4. #724 · Quantexa

    Decision Intelligence platform for fraud and AML

    35Agent
    API Webhooks OAuth2 pythonjava +1
  5. #725 · Hippocratic AI

    Safe AI agents for healthcare

    35Agent
    API
  6. #726 · Abnormal Security

    Protect humans with behavioral AI against phishing, social engineering, and account takeovers.

    35Agent
  7. #727 · Positron AI

    US-built, energy-efficient AI inference chips designed to challenge Nvidia on performance-per-watt.

    35Agent
  8. #728 · Together AI

    The open AI cloud

    35Agent
    API PythonJavaScript +1
  9. #729 · Fireworks AI

    Production-grade generative AI serving

    35Agent
    API PythonJavaScript +1
  10. #730 · Augment Code

    AI agents that understand your entire codebase, from IDE to CLI to code review.

    35Agent
    TypeScript
  11. #731 · Leonardo.Ai

    AI-powered creative suite for image and video generation.

    35Agent
  12. #732 · Dexterity

    Physical AI for warehouse and supply chain robots

    35Agent
    python
  13. #733 · Smartling

    AI translation and localization platform

    35Agent
    API Webhooks OAuth2 javapython +2
  14. #734 · Aleph Alpha

    Specialised language models for a sovereign Europe, designed for real, business-critical environments and decisions.

    35Agent
  15. #735 · Cognite

    Deploy and scale industrial AI to optimize production, reduce downtime, and increase productivity across your enterprise.

    35Agent
    PythonJavaScript
  16. #736 · Scribe

    AI-generated step-by-step process documentation.

    35Agent
  17. #737 · H Company

    Action-oriented agentic foundation models from Paris

    35Agent
    API Webhooks OAuth2 pythontypescript
  18. #738 · Writer

    Full-stack generative AI for enterprise

    35Agent
    API PythonJavaScript
  19. #739 · Glean

    Work AI for the entire enterprise

    35Agent
    API PythonTypeScript +2
  20. #740 · Typeface

    Personalised generative AI for brand content

    35Agent
    API JavaScript
  21. #741 · Hume AI

    Empathic AI voice and emotion intelligence

    35Agent
    API PythonTypeScript
  22. #742 · Lightricks

    The AI technology company empowering creativity through an open ecosystem of AI tools and models.

    35Agent
  23. #743 · Alloy

    The identity and fraud prevention platform for financial services, powered by Actionable AI.

    35Agent
  24. #744 · GMI Cloud

    AI-native inference cloud built for production AI workloads on H100, H200 and Blackwell GPUs.

    35Agent
    API

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.