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
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #865 · Sea AI Lab - SAIL

    Incubating the future by understanding and creating intelligence from first principles to solve challenging problems.

    25Agent
    Python
  2. #866 · ELYZA

    ELYZA is an AI company focused on Deep Learning, developing proprietary large language models and supporting major corporations in their LLM adoption.

    25Agent
  3. #867 · RBC Borealis AI

    Revolutionizing finance through world-class AI research, solutions, and a resilient data platform.

    25Agent
  4. #868 · Shortwave

    AI-native email built on Gmail with bundles, AI search, and chat.

    25Agent
  5. #869 · Krafton AI

    Deep research at the highest level, developing multimodal foundation models for immersive user experiences in gaming and beyond.

    25Agent
  6. #870 · Helicone

    Helicone is an AI gateway and LLM observability platform that helps companies route, debug, and analyze their AI applications.

    25Agent
  7. #871 · Tactiq

    AI Note Taker for Google Meet, Zoom & Teams that transcribes live and summarises instantly.

    25Agent
  8. #872 · Stack AI

    No-code platform for enterprise AI agents and forms

    24Agent
    MCP
  9. #873 · Sweep

    The fastest AI coding assistant for JetBrains IDEs.

    23Agent
    MCP OAuth2
  10. #874 · Endgame

    AI answer engine for enterprise sales teams

    22Agent
    MCP
  11. #875 · Surfer SEO

    AI-powered SEO content optimization platform.

    21Agent
    API
  12. #876 · /dev/agents

    An operating system purpose-built for the era of AI agents.

    20Agent
  13. #877 · Upwind

    Runtime-first cloud security platform

    20Agent
    MCP
  14. #878 · Noma Security

    End-to-end security for agentic AI

    20Agent
    MCP
  15. #879 · GirlfriendGPT

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

    20Agent
  16. #880 · Bright Data

    Unlock the web's data with an all-in-one platform for proxies, web scraping, and AI-ready datasets.

    20Agent
    API
  17. #881 · Gradium

    Ultra-low-latency multilingual voice AI models

    18Agent
    API
  18. #882 · Gigacatalyst

    Customize your software to every user with AI

    18Agent
  19. #883 · Recursion

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

    15Agent
  20. #884 · Wondercraft

    The Canva of audio — generative AI podcasts and ads

    15Agent
    API
  21. #885 · Preferred Networks

    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
  22. #886 · Riverside

    Studio-quality podcast and video recording with AI editing.

    15Agent
  23. #887 · Motion

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

    15Agent
  24. #888 · Imbue

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

    15Agent

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.