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
2443
With MCP
48
Public API
504
OAuth2
86
Avg score
21.7
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2443 tools.

Ranked tools

  1. #745 · NIRAMAI Health Analytix

    A novel AI-based medical device for early, accurate, portable, and privacy-aware breast cancer detection.

    15Agent
  2. #746 · Motion

    AI calendar + project manager that auto-prioritizes your day.

    15Agent
  3. #747 · OpenArt

    AI art generator with multi-model marketplace

    15Agent
  4. #748 · Eve Legal

    The proactive AI workforce for plaintiff law firms, transforming operations from intake to litigation.

    15Agent
  5. #749 · Kodiak AI

    Safely driving an autonomous future with AI-powered ground autonomy solutions for reliable and efficient driverless movement.

    15Agent
  6. #750 · Unstructured

    Transform complex, unstructured data into clean, structured data for GenAI applications, securely and continuously.

    15Agent
  7. #751 · Pano AI

    AI-powered wildfire detection and situational awareness for faster, collaborative response.

    15Agent
  8. #752 · Presight AI

    Presight delivers intelligence designed to work in real-world conditions, supporting decisions and enabling execution for measurable outcomes.

    15Agent
  9. #753 · Robovision

    Robovision provides Industrial Vision Intelligence Infrastructure to monitor, control, and standardize vision systems for outcome assurance at scale.

    15Agent
  10. #754 · Trigo

    AI-powered grocery digitization with autonomous checkout.

    15Agent
  11. #755 · PKSHA Technology Inc.

    PKSHA Technology develops and implements AI-powered software that co-evolves with people to solve business challenges and societal issues.

    15Agent
  12. #756 · Lofty

    AI CRM and marketing platform for real estate agents.

    15Agent
  13. #757 · Spellbook

    AI contract review for lawyers

    15Agent
  14. #758 · Stilta

    Agentic AI for high-stakes patent work, enabling rapid invalidity, infringement, and FTO analyses across vast data sources.

    15Agent
  15. #759 · TopView AI

    Viral video generator from any script or product link

    15Agent
  16. #760 · EvenUp

    AI for personal injury law

    15Agent
  17. #761 · Imbue

    Tools to empower humans in the AI age with reliable, collaborative coding agents.

    15Agent
  18. #762 · Chatbase

    Custom AI chatbots trained on your data.

    15Agent
    JavaScript
  19. #763 · Above Security

    AI-agent platform for insider-threat detection

    15Agent
    OAuth2
  20. #764 · Codeium

    Free AI coding superpower for every developer

    13Agent
  21. #765 · Tasklet

    The cloud agent operating system for knowledge work

    12Agent
  22. #766 · Multifactor

    Zero-trust authentication, authorization, and auditing for AI agents

    12Agent
  23. #767 · KERNEL

    Crazy fast, open source infra for AI agents to use the Internet

    12Agent
  24. #768 · Lucent

    AI that automatically improves products from user behavior

    12Agent

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: MCP support (20pt), public API (20pt), webhooks (15pt), developer docs quality (15pt), SDK breadth (15pt), OAuth/auth completeness (15pt). Score is the weighted sum, rechecked weekly via automated scrapes.

›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.