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
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #961 · Nexus

    We help non-technical teams build AI agents without engineers

    12Agent
  2. #962 · Veritus

    AI agents for the consumer lending industry

    12Agent
  3. #963 · Dedalus Labs

    Compute substrate for AI agents

    12Agent
  4. #964 · AgentMail

    Email Inboxes for AI Agents

    12Agent
  5. #965 · Vulcan Technologies

    AI for every law, regulation, and court case

    12Agent
  6. #966 · Uplift AI

    Foundational Voice Models for regional languages

    12Agent
  7. #967 · Stellon Labs

    Building tiny frontier AI models that run on edge devices

    12Agent
  8. #968 · Wedge

    Palantir for Healthcare AI Agents

    12Agent
  9. #969 · Maywood

    The first finance-compliant proactive AI that runs 24/7

    12Agent
  10. #970 · Vela

    AI Agents For Complex Scheduling Coordination

    12Agent
  11. #971 · Terminal Use

    Vercel for background agents

    12Agent
  12. #972 · Corvera

    The context layer for AI-native CPG brands

    12Agent
  13. #973 · Ritivel

    AI-native platform for Life-Sciences Documentation

    12Agent
  14. #974 · Sponge

    Financial infrastructure for the agent economy

    12Agent
  15. #975 · LegalOS

    The AI-Native Immigration Law Firm

    12Agent
  16. #976 · 10x Science

    The AI-native platform for next-generation protein characterization

    12Agent
  17. #977 · Valgo

    Insurance risk layer for physical AI

    12Agent
  18. #978 · Syntropy

    The agentic coding app for complex tasks

    12Agent
  19. #979 · ProjectX

    Infinity: the first OS where humans and agents work with no limits

    12Agent
  20. #980 · Kimpton AI

    AI for portfolio managers

    12Agent
  21. #981 · YouArt

    Patreon for AI originals

    12Agent
  22. #982 · Auxos

    AI customer clones for market research

    12Agent
  23. #983 · tday.com

    AI that turns your product into on-brand marketing content

    12Agent
  24. #984 · Napkin Math

    The hyper-personalized AI food journal

    12Agent

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.