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. #409 · indigo.ai

    Automate conversations with AI Agents to manage complex tasks and speak with your brand's voice.

    45Agent
  2. #410 · Unify

    Unify brings together Sales, Marketing, Growth, and RevOps under one roof to clarify attribution and streamline outbound strategies.

    45Agent
  3. #411 · Inception

    Inception's breakthrough diffusion-based approach enables the world’s fastest, most efficient AI models with best-in-class quality.

    45Agent
  4. #412 · Slang AI

    The #1 Voice AI tool for restaurants, acting as an AI Superhost to manage reservations and guest inquiries 24/7.

    45Agent
  5. #413 · NVIDIA Run:ai

    The enterprise platform for AI workloads and GPU orchestration.

    45Agent
  6. #414 · Notable

    The AI Platform purpose-built for healthcare, automating the work behind the care with AI Agents.

    45Agent
  7. #415 · Argil

    Generate high-performing videos with your AI clone or choose from engaging avatars for promotion, education, and entertainment.

    45Agent
  8. #416 · Encord

    The multimodal data layer powering physical AI from training to real-world deployment.

    45Agent
  9. #417 · CoreWeave

    The Essential Cloud for AI, purpose-built to power pioneers' most complex workloads with next-generation infrastructure and intelligent tools.

    44Agent
    API
  10. #418 · Hour One

    AI digital humans and virtual twins for video at scale

    44Agent
    API Webhooks OAuth2 rest
  11. #419 · Nscale

    European sovereign AI infrastructure

    43Agent
    API
  12. #420 · Inflection AI

    Personal AI for everyone

    43Agent
    API
  13. #421 · MultiOn

    AI agent that takes actions on the web

    42Agent
    API pythontypescript
  14. #422 · Thinking Machines Lab

    Frontier AI research lab building customizable, multimodal models

    41Agent
    API python
  15. #423 · Lambda

    GPU cloud for AI teams

    41Agent
    API Python
  16. #424 · Aidoc

    Clinical AI foundation model for medical imaging and triage

    40Agent
    API
  17. #425 · Pudu Robotics

    Commercial service robots for delivery, cleaning, and beyond

    40Agent
    API
  18. #426 · Gecko Robotics

    AI and robotics for inspecting critical infrastructure

    40Agent
    API
  19. #427 · Feedzai

    We keep the world's money moving safely

    40Agent
    API
  20. #428 · Tractable

    Computer-vision AI for insurance damage appraisal

    40Agent
    API
  21. #429 · Invisible Technologies

    AI training data and enterprise automation platform

    40Agent
    API
  22. #430 · Alcatraz AI

    AI facial authentication that replaces the access badge with your face

    40Agent
    API
  23. #431 · Proscia

    AI-powered digital pathology for precision medicine

    40Agent
    API
  24. #432 · Typecast

    Emotionally expressive AI voices and virtual actors

    40Agent
    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.