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. #1705 · Leo AI

    The first generative AI copilot built for mechanical engineering and CAD

    10Agent
  2. #1706 · FieldAI

    Physics-first foundation models that are universal brains for robots

    10Agent
  3. #1707 · Wabi

    The YouTube of apps: prompt to instantly build and share mini-apps

    10Agent
  4. #1708 · FleetWorks

    An always-on AI dispatcher that matches trucks with freight

    10Agent
  5. #1709 · Ankar

    AI platform that streamlines how companies and law firms capture, file and manage patents

    10Agent
  6. #1710 · Brightband

    AI weather and climate forecasting company building an end-to-end Earth System model trained

    10Agent
  7. #1711 · Silurian

    Earth intelligence company building foundation models to simulate the planet, starting with

    10Agent
  8. #1712 · Odyssey

    AI research lab building world models that generate and stream interactive 3D environments in

    10Agent
  9. #1713 · DualEntry

    AI-native ERP platform built for the mid-market that automates up to 90% of manual accounting

    10Agent
  10. #1714 · Maisa

    Accountable, hallucination-resistant AI agents called 'Digital Workers' that automate complex

    10Agent
  11. #1715 · Sinai.ai

    Egyptian education-AI company turning licensed books into interactive, AI-native reading

    10Agent
  12. #1716 · Yozo.ai

    Abu Dhabi-based startup building an AI-native revenue engine for e-commerce merchants

    10Agent
  13. #1717 · Vambe

    Santiago, Chile-based startup whose AI agents automate sales conversations and customer

    10Agent
  14. #1718 · Orchid Security

    AI-powered identity security platform that uses large language models to bring clarity to

    10Agent
  15. #1719 · Twine Security

    AI 'digital employees' that autonomously execute cybersecurity work alongside human teams

    10Agent
  16. #1720 · TinyFish

    Enterprise web agents that simulate human-like browsing to automate repetitive, web-based

    10Agent
  17. #1721 · Isara

    San Francisco startup building software to coordinate thousands of specialized AI agents into

    10Agent
  18. #1722 · Mimic Robotics

    Zurich-based, ETH spin-off building physical-AI systems that learn dexterous manipulation from

    10Agent
  19. #1723 · Aalo Atomics

    Designs mass-manufactured nuclear power plants purpose-built to power AI data centers and

    10Agent
  20. #1724 · Cohere Health

    Clinical intelligence company that uses AI to transform prior authorization and utilization

    10Agent
  21. #1725 · Featherless.ai

    Serverless inference platform that hosts thousands of open-source AI models behind a single

    10Agent
  22. #1726 · Alinia AI

    Barcelona-based startup building compliance and guardrails infrastructure for enterprise AI

    10Agent
  23. #1727 · Bindwell

    Applies AI-driven molecular discovery techniques, originally developed for drug discovery, to

    10Agent
  24. #1728 · 2wai

    Social app for AI avatars that lets anyone create a conversational 'HoloAvatar' digital twin

    10Agent

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.