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. #2329 · Reflect

    AI-powered note-taking app designed to mirror the way you think, linking notes into a

    10Agent
  2. #2330 · Elysian

    AI-native third-party administrator (TPA) built for commercial insurance claims

    10Agent
  3. #2331 · Ridley

    AI-powered real estate platform that lets homeowners sell their homes without paying the

    10Agent
  4. #2332 · Spocket

    Dropshipping marketplace sourcing products from US and EU suppliers

    10Agent
    OAuth2
  5. #2333 · Midjourney

    Independent AI image generation lab.

    10Agent
  6. #2334 · Common Room

    An AI-native GTM platform that powers pipeline generation with precise buyer intelligence.

    10Agent
  7. #2335 · ClimateAi

    Minimize climate risk and maximize future opportunities with hyper-local, AI-powered climate insights for food and agriculture.

    10Agent
  8. #2336 · Mujin

    Intelligent industrial robotics OS for manufacturing and logistics

    10Agent
  9. #2337 · Tortus

    UK-based clinical AI company building an AI co-pilot, branded OSLER, that automates clinical

    10Agent
  10. #2338 · Brand.AI

    AI brand management platform that makes brand guidelines and strategy machine-readable so AI

    10Agent
  11. #2339 · Laxis

    AI meeting assistant focused on revenue teams, capturing notes, transcribing conversations

    10Agent
  12. #2340 · Welltory

    The one app for your health — AI-powered insights to reduce stress, boost energy, and sleep better

    10Agent
  13. #2341 · Sakana AI

    An AI R&D company based in Tokyo, Japan, focused on developing AI solutions tailored for Japan's needs and democratizing AI.

    10Agent
  14. #2342 · Etched

    Etched is building custom hardware to accelerate large language models and achieve superintelligence.

    10Agent
  15. #2343 · Integral AI

    Self-learning AI models for industrial robots and autonomous systems

    10Agent
  16. #2344 · Nectar

    The AI Social OS Bridging Community with Revenue.

    10Agent
  17. #2345 · Hark

    Energy Management Software for Commercial & Industrial Buildings & Assets.

    10Agent
  18. #2346 · Serra

    AI sourcing agent that finds, scores and ranks candidates from plain-English roles

    10Agent
  19. #2347 · Bluedot

    Bot-free AI meeting notetaker that records, transcribes, and summarizes meetings without

    10Agent
  20. #2348 · OpenCode

    Open-source terminal AI coding agent — Aider alternative with multi-model support

    10Agent
    bash
  21. #2349 · Genesia AI

    Customizable AI friend and partner chatbot from app studio Codeway

    10Agent
  22. #2350 · Geostar

    Generative engine optimization to win AI search visibility

    10Agent
  23. #2351 · Hazel

    AI procurement software for government

    10Agent
    OAuth2
  24. #2352 · Andy AI

    AI clinical documentation for home health

    10Agent
    OAuth2

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.