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

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #2281 · Deepull

    Barcelona medical diagnostics company developing UllCORE, a rapid direct-from-blood

    10Agent
  2. #2282 · Onyx

    Onyx, formerly Danswer, is an open-source enterprise AI search and assistant that connects to

    10Agent
  3. #2283 · DEEPX

    South Korean semiconductor startup designing on-device AI chips, or neural processing units

    10Agent
  4. #2284 · SiMa.ai

    Machine-learning system-on-chip (MLSoC) hardware that runs multimodal and generative AI at the

    10Agent
  5. #2285 · Salience Labs

    Silicon photonics startup building all-optical switches for large-scale AI data center

    10Agent
  6. #2286 · Skymizer

    Taiwanese company building AI compiler technology and IP for efficient edge inference

    10Agent
  7. #2287 · Kashable

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

    10Agent
  8. #2288 · Buildots

    AI construction progress tracking with helmet-mounted 360 cameras.

    10Agent
  9. #2289 · Lexroom

    Italian legal AI platform for research, drafting, and advisory across European jurisdictions.

    10Agent
  10. #2290 · Kindroid

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

    10Agent
  11. #2291 · Akido Labs

    AI-powered clinical decision support tackling the physician shortage with ScopeAI.

    10Agent
  12. #2292 · Cera

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

    10Agent
  13. #2293 · Aignostics

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

    10Agent
  14. #2294 · Summer Health

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

    10Agent
  15. #2295 · Fabric

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

    10Agent
  16. #2296 · Flex

    All-in-one AI-powered financial platform for mid-sized businesses, unifying private credit

    10Agent
  17. AI-powered financial planning platform that helps advisors deliver personalized, real-time

    10Agent
  18. #2298 · Kick

    AI-native bookkeeping platform that automates accounting for small businesses and accounting

    10Agent
  19. #2299 · VODA.ai

    AI decision-support platform for water utilities that predicts pipe failures and prioritizes

    10Agent
  20. #2300 · C the Signs

    AI platform that identifies patients at risk of cancer at the earliest, most curable stage

    10Agent
  21. #2301 · Ensocell

    Cambridge, UK biotech that integrates single-cell and spatial genomics with AI to discover

    10Agent
  22. #2302 · Supernormal

    AI meeting notes platform that joins Zoom, Google Meet, and Microsoft Teams calls to

    10Agent
  23. #2303 · Mindy

    Email-based AI personal assistant that you interact with simply by sending and CC'ing emails

    10Agent
  24. #2304 · Bloks

    AI-powered productivity assistant that captures and organizes meeting notes, then surfaces

    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.