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. #2113 · Round

    AI-powered finance automation platform that executes treasury, accounts payable, and payroll

    10Agent
  2. #2114 · Userled

    AI-powered platform that helps B2B companies create and manage personalized marketing

    10Agent
  3. #2115 · WIZ.AI

    Singapore-based enterprise voice AI company that builds humanlike voice agents (Talkbots) for

    10Agent
  4. #2116 · Kombai

    Domain-specific AI coding agent built specifically for front-end development

    10Agent
  5. #2117 · Neuron7

    Service-resolution intelligence platform that uses AI to help technical support, field

    10Agent
  6. #2118 · Rapidata

    Zurich-based AI infrastructure company building a real-time, global human-feedback network for

    10Agent
  7. #2119 · Cleric

    AI site reliability engineer that autonomously investigates production alerts, performs

    10Agent
  8. #2120 · Vannevar Labs

    AI-powered intelligence and electronic warfare software for national security

    10Agent
  9. Real-time radio-frequency sensing and signals intelligence

    10Agent
  10. #2122 · Array Labs

    3D maps of Earth from formation-flying radar satellites

    10Agent
  11. #2123 · Commure

    Full-stack healthcare AI platform that unifies revenue cycle management, ambient clinical

    10Agent
  12. #2124 · Vizcom

    AI-powered design platform that turns rough sketches and 2D drawings into photorealistic

    10Agent
  13. #2125 · BLNG

    Generative AI platform for the luxury jewelry industry that turns sketches into photorealistic

    10Agent
  14. #2126 · Nectir

    Purpose-built AI infrastructure for higher education, letting institutions create custom AI

    10Agent
  15. #2127 · Momentum

    AI-powered customer intelligence platform that turns sales calls, emails, and Slack

    10Agent
  16. #2128 · Floworks

    Autonomous AI sales employees that automate the B2B prospecting journey, led by its AI SDR

    10Agent
  17. #2129 · Zania

    Agentic AI platform for enterprise governance, risk, and compliance (GRC) that helps security

    10Agent
  18. Israeli surgical-robotics company building ORYOM, described as the world's first robotic

    10Agent
  19. #2131 · OroraTech

    German space-tech company that detects and monitors wildfires using its own constellation of

    10Agent
  20. #2132 · Infravision

    Aerial-robotics systems that string and maintain high-voltage power lines using autonomous

    10Agent
  21. #2133 · ego AI

    A character engine that combines small language models with reinforcement learning to create

    10Agent
  22. #2134 · Muun AI

    Singapore-based industrial intelligence startup whose platform reads data from industrial

    10Agent
  23. #2135 · Accend

    Provides an end-to-end AI platform that helps commercial banks and fintechs underwrite

    10Agent
  24. #2136 · Prosperr.io

    Bengaluru-based fintech building AI-powered tax management infrastructure for both businesses

    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.