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. #2305 · Prenosis

    Precision medicine company building AI-based diagnostics for acute and critical care

    10Agent
  2. #2306 · Tracksuit

    Always-on brand tracking and analytics platform that measures brand health metrics like

    10Agent
  3. #2307 · Activeloop

    Deep Lake, a database and data infrastructure purpose-built for AI that stores and streams

    10Agent
  4. #2308 · Mangomint

    Next-generation salon and spa management platform built around automation

    10Agent
  5. #2309 · Functionize

    AI-powered software test automation platform that uses agentic AI to create, execute, and

    10Agent
  6. #2310 · Seeing Systems

    Modular AI-commanded autonomous strike drones built for contested combat environments.

    10Agent
  7. #2311 · Suki

    AI voice assistant for clinicians that uses generative AI to ambiently create clinical

    10Agent
  8. #2312 · Navina

    Clinical AI company whose copilot transforms scattered healthcare data into actionable

    10Agent
  9. #2313 · Regard

    Healthcare AI company that builds an AI co-pilot for physicians, automatically analyzing

    10Agent
  10. #2314 · Corti

    Copenhagen-based healthcare AI company building specialized foundation models and a clinical

    10Agent
  11. #2315 · Wealth.com

    AI-powered estate and tax planning platform for wealth management firms and financial advisors

    10Agent
  12. #2316 · Daylit

    AI agents platform for accounts receivable that automates collections, dispute resolution, and

    10Agent
  13. #2317 · Truewind

    AI-powered accounting and bookkeeping platform that automates financial document processing

    10Agent
  14. #2318 · FarmDroid

    Danish agritech company that makes the world's first solar-powered field robot to both seed

    10Agent
  15. #2319 · Burro

    US-based agricultural robotics company that makes autonomous, collaborative ground robots for

    10Agent
  16. #2320 · Wealthy

    Bengaluru-based wealthtech platform that gives mutual fund distributors a mobile-first toolkit

    10Agent
  17. #2321 · Influur

    Professional networking and influencer marketing platform that connects brands with creators

    10Agent
  18. #2322 · Kashable

    Kashable provides socially responsible financing and financial wellness solutions to employees as an employer-sponsored voluntary benefit.

    10Agent
  19. #2323 · Buildots

    AI construction progress tracking with helmet-mounted 360 cameras.

    10Agent
  20. #2324 · Kindroid

    Build deeply customizable AI companions with real memories, AR calls, and encrypted chat.

    10Agent
  21. #2325 · Cera

    AI-powered home healthcare that predicts and prevents health deterioration.

    10Agent
  22. #2326 · Aignostics

    Berlin-based computational pathology company building AI foundation models that analyze tissue

    10Agent
  23. #2327 · Summer Health

    Text-based pediatric care service that pairs parents with pediatricians over messaging and

    10Agent
  24. #2328 · Fabric

    AI-powered care enablement company that consolidates fragmented healthcare technology into a

    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.