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

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #1657 · DeepIP

    AI patent intelligence platform that assists IP attorneys with drafting, prosecuting and

    10Agent
  2. #1658 · Neysa

    India-based AI cloud platform offering GPU-as-a-service for training, fine-tuning, and

    10Agent
  3. #1659 · CX2

    AI-enabled electronic warfare across the electromagnetic spectrum

    10Agent
  4. #1660 · Maze

    AI-native cloud security platform that uses autonomous AI agents to investigate, prioritize

    10Agent
  5. AI governance company that helps enterprises safely adopt AI at scale by mapping, monitoring

    10Agent
  6. #1662 · Catena Labs

    Building the first AI-native financial institution, providing payment and identity

    10Agent
  7. #1663 · Modus

    AI-native audit technology platform and holding company that partners with established

    10Agent
  8. #1664 · Orbio

    Madrid-based startup building what it calls the world's first AI-native human capital

    10Agent
  9. #1665 · Orasio

    Paris-based deep-tech startup building sovereign video intelligence technology for European

    10Agent
  10. #1666 · BEKHealth

    Uses AI and natural language processing to accelerate clinical trial patient recruitment from

    10Agent
  11. #1667 · Senai

    Israeli startup building Online Video Intelligence (OVINT), using multimodal AI to turn

    10Agent
  12. #1668 · Wudpecker

    Multilingual AI meeting assistant that records, transcribes, and summarizes calls into

    10Agent
  13. #1669 · ValueMate

    Automates residential real estate appraisals with an AI-plus-LiDAR mobile app that captures a

    10Agent
  14. #1670 · Reka AI

    Multimodal AI models for the enterprise

    10Agent
    API Python
  15. #1671 · Atomicwork

    Agentic ITSM and employee service platform

    10Agent
    API Webhooks OAuth2 pythontypescript
  16. #1672 · Plus AI

    AI presentation maker for Google Slides and PowerPoint

    10Agent
    OAuth2
  17. #1673 · Nevis

    Unified AI platform that automates back-office workflows for RIAs and wealth advisors.

    10Agent
  18. Generative AI and ultra-high-throughput chemistry for small-molecule drug discovery

    10Agent
  19. #1675 · AI Proteins

    Designing a new class of de novo miniprotein medicines with AI

    10Agent
  20. #1676 · Valerie Health

    AI front office for independent doctors' practices

    10Agent
  21. #1677 · Orchard Robotics

    AI-powered farm vision that tracks the health and yield of millions of plants

    10Agent
  22. #1678 · Lumai

    3D optical computing that slashes the cost and power of AI inference.

    10Agent
  23. #1679 · AI Hay

    AI-powered knowledge discovery and Q&A platform for Vietnamese users

    10Agent
  24. #1680 · CyberRidge

    Photonic encryption that hides data as optical noise, quantum-resistant by design

    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.