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

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #1705 · TestSprite

    Autonomous AI testing platform built to be the testing backbone for AI-native software

    10Agent
  2. #1706 · Phoebe

    Building an AI-driven immune system for software, using swarms of AI agents that continuously

    10Agent
  3. #1707 · Thena

    AI customer support platform purpose-built for B2B teams that serve customers in Slack

    10Agent
  4. #1708 · Topview

    Singapore-based AI content platform that uses proprietary AI and digital human technology to

    10Agent
  5. #1709 · ValkaAI

    Czech startup building a real-time interactive AI video platform that lets businesses deploy

    10Agent
  6. #1710 · Delphi

    Lets experts and creators build a 'Digital Mind,' an interactive AI clone trained on their

    10Agent
  7. #1711 · Arcade

    Authenticated tool-calling platform that lets AI agents take secure, real-world actions on

    10Agent
  8. #1712 · Deeptune

    High-fidelity reinforcement learning environments, or training gyms, that simulate

    10Agent
  9. #1713 · Payman AI

    Agentic banking infrastructure that lets AI agents execute real financial transactions

    10Agent
  10. #1714 · Sand AI

    Chinese generative video company behind MAGI, an autoregressive video generation model

    10Agent
  11. #1715 · Neural Concept

    Swiss CAD-native AI platform that brings deep-learning surrogate models and generative design

    10Agent
  12. #1716 · ChipAgents

    ChipAgents, built by Alpha Design AI, is an agentic AI platform for semiconductor design and

    10Agent
  13. #1717 · Cognichip

    AI-first semiconductor company building what it calls Artificial Chip Intelligence (ACI), a

    10Agent
  14. #1718 · eNOugh

    London-based safety-technology startup building an AI-powered wearable personal safety device

    10Agent
  15. #1719 · Pickle

    Real-time AI video clone for calls

    10Agent
    OAuth2
  16. #1720 · Mem

    Self-organising workspace powered by AI

    10Agent
  17. #1721 · Krea AI

    AI image generation in real-time

    10Agent
    API
  18. #1722 · MagicSchool

    AI for teachers

    10Agent
  19. #1723 · DeepBrain AI

    Transform text into captivating videos with AI-powered avatars and intuitive editing

    10Agent
  20. #1724 · Sanctuary AI

    Creating and deploying industrial-grade humanoid robots that work and think like people to address global labor challenges.

    10Agent
  21. #1725 · Nooks

    AI sales assistant for prospecting and dialing

    10Agent
    API Webhooks OAuth2 javascript
  22. #1726 · Onton

    Neuro-symbolic AI shopping site for product discovery

    10Agent
  23. #1727 · Vox AI

    Autonomous voice AI for restaurant drive-thrus

    10Agent
  24. #1728 · Nucleus Genomics

    AI-powered whole-genome DNA analysis for proactive health and family planning

    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.