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. #2569 · Ellis

    The AI-native operations platform for private credit, providing a single trusted book for fund management.

    10Agent
  2. #2570 · inforcer

    Standardise Microsoft 365 policies and manage Copilot across multiple tenants for MSPs.

    10Agent
  3. #2571 · Omilia

    Conversational AI solutions that continuously learn from real outcomes to improve customer experience.

    10Agent
  4. #2572 · Cleerly

    FDA-cleared AI imaging platform that analyzes coronary CT scans to detect and characterize heart disease earlier.

    8Agent
  5. #2573 · Day.ai

    An AI-native CRM that builds itself from your emails, meetings, and conversations.

    8Agent
  6. #2574 · Shield AI

    Autonomous AI software for defence

    8Agent
  7. #2575 · Grit.io

    Automated code migrations — upgrade frameworks and dependencies with AI

    8Agent
  8. #2576 · v0

    Build agents, apps, and websites with AI — generate working frontends in minutes

    8Agent
  9. #2577 · HeraHaven AI

    Customizable AI girlfriend app operated by Cyprus-based Vilala Limited.

    8Agent
  10. #2578 · GoLove AI

    Multi-mode AI companion platform by Cyprus-based 404 Intelligence Ltd with chat, voice, image, and video.

    8Agent
  11. #2579 · Secrets.ai

    Privacy-focused 18+ AI companion platform with realistic girlfriend chat, images, and video.

    8Agent
  12. #2580 · Muah AI

    Uncensored AI companion app notable for its September 2024 data breach and CSAM-prompt controversy.

    8Agent
  13. #2581 · Roofline

    Retargetable AI compiler for edge hardware deployment

    7Agent
  14. #2582 · Niantic Spatial

    Real-world foundation models and AR maps for physical AI

    6Agent
    unityswift +1
  15. #2583 · Bedrock Robotics

    Autonomous retrofits that turn construction equipment into self-driving fleets

    5Agent
  16. #2584 · LlamaIndex

    Data framework and cloud for LLM applications

    5Agent
  17. #2585 · Bolt.new

    Full-stack apps from a single prompt — deployed in seconds by StackBlitz

    5Agent
    MCP
  18. #2586 · Udio

    Discover, create, and share music with AI.

    5Agent
  19. #2587 · Slingshot AI

    Foundation model and AI app for mental health

    5Agent
  20. #2588 · Upscale AI

    Pure-play AI networking infrastructure

    5Agent
  21. #2589 · Covariant

    AI robots that learn and generalise

    5Agent
    API
  22. #2590 · Synthesis

    Math and reasoning for ambitious kids

    5Agent
  23. #2591 · Granola

    AI notepad for back-to-back meetings

    5Agent
    API
  24. #2592 · Limitless

    Limitless, a pioneer in AI-enabled wearables and personal superintelligence, has been acquired by Meta to advance their shared vision.

    5Agent

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.