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. #745 · Coda

    Coda is your all-in-one collaborative workspace, bringing teams and tools together for a more organized and productive workday.

    35Agent
  2. #746 · Pricefx

    Cloud-native pricing optimization with AI rebate management.

    35Agent
  3. #747 · Vectra AI

    Cybersecurity AI that stops attacks others can’t by revealing who's doing what on your network right now.

    35Agent
  4. #748 · JetBrains AI Assistant

    AI inside IntelliJ, PyCharm, WebStorm — code without leaving your JetBrains IDE

    35Agent
    KotlinJava
  5. #749 · Abridge

    Enterprise-grade AI for clinical conversations, trusted by the largest healthcare systems to improve outcomes at scale.

    35Agent
  6. #750 · Vespa.ai

    Big-data serving engine for vector and lexical search

    35Agent
    API Webhooks OAuth2 pythonjava +1
  7. #751 · Nabla

    Smarter clinical workflows and elevated care through ambient AI, dictation, and real-time intelligence for healthcare professionals.

    35Agent
  8. #752 · Sublime Security

    Autonomous email defense for the post-LLM threat era

    35Agent
    API Webhooks OAuth2 pythongo
  9. #753 · Imagen

    Personal AI photo editing assistant for photographers

    35Agent
    API OAuth2 rest
  10. #754 · Multiverse Computing

    Pioneering the era of efficient and secure AI by empowering organisations to run production-ready AI with tailored solutions.

    35Agent
    Python
  11. #755 · Lexion

    AI contract management for fast-moving teams

    35Agent
    API
  12. #756 · Gamma

    Effortless AI design for presentations, websites, and more, helping you create captivating content almost as quickly as you can think it up.

    35Agent
  13. #757 · Robin AI

    Get instant insights from your legal documents with Robin's AI-powered Legal Intelligence Platform.

    35Agent
  14. #758 · Tavus

    AI video personalization platform

    35Agent
    API JavaScriptPython
  15. #759 · Ada

    AI customer service automation platform

    35Agent
    API iOS (Swift)React Native +1
  16. #760 · Endgame

    AI answer engine for enterprise sales teams

    35Agent
    API Webhooks OAuth2 rest
  17. #761 · Indexable

    Sandbox infrastructure for AI agents with millisecond full-environment forks.

    35Agent
  18. #762 · AssemblyAI

    AI models for accurate speech recognition

    35Agent
    API PythonTypeScript +5
  19. #763 · Kore.ai

    Conversational AI for enterprise customer experience

    35Agent
    API JavaScript
  20. #764 · ROGO Agriculture

    Autonomous robots that collect agronomic soil and plant data.

    35Agent
  21. #765 · ReasonBlocks

    Agent runtime that catches mid-run failures and builds a private reasoning library.

    35Agent
  22. #766 · Virtuals Protocol

    The leading tokenized AI agent launchpad on the Base blockchain.

    35Agent
  23. #767 · Fractal Analytics

    Power enterprise decisions with AI that works, transforming organizations with AI engineered for scale and designed for impact.

    35Agent
  24. #768 · Korso

    The intelligence layer for manufacturing that automates RFQs, supplier comms, and production exceptions.

    35Agent

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.