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

Filter tools

Filters

Showing 24 of 2443 tools.

Ranked tools

  1. #721 · Nectar AI

    Venture-backed generative AI companion platform building uncensored, immersive AI girlfriends.

    20Agent
  2. #722 · Caveduck

    Korean AI character chat platform with creator revenue sharing, backed by a $2.85M Series A.

    20Agent
  3. #723 · Janitor AI

    Free character roleplay chatbot platform with a proprietary uncensored LLM (JLLM) and 15M+ users.

    20Agent
  4. #724 · SpicyChat AI

    Free uncensored AI character roleplay platform by NextDay AI, with 100M+ registered users.

    20Agent
  5. #725 · GirlfriendGPT

    AI girlfriend and companion chat platform by NextDay AI, with custom voice and image generation.

    20Agent
  6. #726 · 7AI

    Agentic cybersecurity platform deploying autonomous AI security agents for alert triage and investigation.

    20Agent
  7. #727 · Crosby

    AI-native law firm delivering fast contract review through a Slack-native, services-as-software model.

    20Agent
  8. #728 · Rox

    AI agent swarms that put enterprise revenue on autopilot for the Global 2000.

    20Agent
  9. #729 · Definite

    One AI-native data platform that replaces the entire modern data stack.

    20Agent
  10. #730 · TensorWave

    AI cloud built on AMD Instinct accelerators, operating one of the world's largest liquid-cooled AMD GPU deployments.

    20Agent
  11. #731 · Positron AI

    US-built, energy-efficient AI inference chips designed to challenge Nvidia on performance-per-watt.

    20Agent
  12. #732 · Lila Sciences

    Building scientific superintelligence and autonomous AI labs for life, chemical and materials sciences.

    20Agent
  13. #733 · Gigacatalyst

    Customize your software to every user with AI

    18Agent
  14. #734 · Gradium

    Ultra-low-latency multilingual voice AI models

    18Agent
    API
  15. #735 · Dash0

    AI-native observability platform built on OpenTelemetry

    15Agent
  16. #736 · Wonderful

    Multilingual enterprise AI agents for customer service

    15Agent
  17. #737 · Recursion

    Pioneering AI-driven solutions in drug discovery to radically improve lives.

    15Agent
  18. #738 · Owkin

    Pioneering biological artificial superintelligence to automate R&D and connect research directly to patient care.

    15Agent
  19. #739 · Glance

    Your intelligent shopping agent for smarter style, understanding your preferences and evolving with every interaction.

    15Agent
  20. Preferred Networks develops and provides all four layers of the AI technology value chain: AI semiconductors, computing infrastructure, generative AI foundation models, and AI products/solutions.

    15Agent
  21. #741 · OpenSpace

    AI-powered construction site documentation via 360-degree video.

    15Agent
  22. #742 · Riverside

    Studio-quality podcast and video recording with AI editing.

    15Agent
  23. #743 · Patronus AI

    A frontier lab training the first Digital World Models to simulate and predict agent actions in digital workflows.

    15Agent
  24. #744 · Supermaven

    The fastest code autocomplete — 1M token context, instant suggestions

    15Agent
    TypeScriptPython +1

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.