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. #2233 · Aerones

    Latvia-based company providing AI-driven robotic maintenance and inspection for wind turbines

    10Agent
  2. #2234 · Zencoder

    AI coding agent paired with Zenflow, an orchestration layer that automates the broader

    10Agent
  3. #2235 · Dixa

    Agentic AI customer service platform built for ecommerce and consumer brands

    10Agent
  4. #2236 · Capacity

    AI-powered support automation platform that helps contact centers and teams deflect tickets

    10Agent
  5. #2237 · Speechify

    Turn any text into natural audio with AI

    10Agent
    PythonTypeScript
  6. #2238 · Sereact

    Physical AI that delivers real autonomy on the warehouse floor, operating with zero supervision and infinite precision.

    10Agent
  7. #2239 · Hyper

    Self-driving company brain that silently learns from every tool your team uses.

    10Agent
  8. #2240 · Aster

    The first AI-native AI research lab using agentic workflows to accelerate model discovery.

    10Agent
  9. #2241 · matforge

    AI scientists that discover next-generation semiconductor materials in months instead of a decade.

    10Agent
  10. #2242 · WithAI

    Custom AI command centers that let hedge fund analysts research and manage portfolios with agents.

    10Agent
  11. #2243 · Klarify

    AI agent for therapists that writes clinical notes, treatment plans, and insurance claims automatically.

    10Agent
  12. #2244 · VERO

    AI risk and screening OS for multifamily leasing

    10Agent
  13. #2245 · Dippy AI

    Censorship-free AI characters and roleplay companions, free and unlimited

    10Agent
  14. #2246 · Buddy.ai

    AI English tutor for kids using voice-based learning games

    10Agent
  15. #2247 · Barreleye

    Korean medical AI startup developing ultrasound-based diagnostic solutions powered by deep

    10Agent
  16. #2248 · mayk.it

    Music-creation and marketing platform that gives artists and fans AI-powered tools to make and

    10Agent
  17. #2249 · Soundverse

    AI music-creation platform and assistant that helps creators generate, edit, and produce music

    10Agent
  18. #2250 · Insight Terra

    Climate-tech SaaS company providing an AI-powered platform for environmental risk management

    10Agent
  19. #2251 · Renewable Metals

    Australian battery-recycling company that has developed a world-first alkali-based

    10Agent
  20. #2252 · Spellbrush

    Generative AI studio specializing in anime-style art for video games, and is the team behind

    10Agent
  21. #2253 · SquadStack

    India-based platform that blends AI voice agents with a managed network of trained

    10Agent
  22. #2254 · SPREAD

    Berlin-based industrial AI company building an Engineering Intelligence platform for complex

    10Agent
  23. #2255 · Quandela

    French quantum-computing company building photonic quantum computers and cloud access to them

    10Agent
  24. #2256 · NOSIBLE

    South African AI company that builds a high-performance search engine and event database for

    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.