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. #1969 · Miraterra

    AI-driven soil intelligence combining spectroscopy, genomics, and machine learning

    10Agent
  2. #1970 · Parambil

    AI-powered medical record review for mass tort and complex litigation.

    10Agent
  3. #1971 · Soxton AI

    AI-native legal copilot that gives startups affordable, on-demand legal support.

    10Agent
  4. #1972 · Justpoint

    AI that uncovers product harms and powers mass tort and personal injury litigation.

    10Agent
  5. #1973 · Airial

    AI travel concierge that plans every detail of your trip

    10Agent
  6. #1974 · Q Concierge

    Voice AI infrastructure that answers every hotel call

    10Agent
  7. #1975 · SOUS

    The AI-powered sous chef for restaurant growth

    10Agent
  8. #1976 · Rosella

    AI automation platform for commercial insurance brokers

    10Agent
  9. #1977 · Arlo

    AI-powered level-funded health plans for small businesses

    10Agent
  10. #1978 · Spines

    AI-powered publishing platform that helps authors publish books fast

    10Agent
  11. #1979 · No Barrier

    Real-time, HIPAA-compliant AI medical interpretation in 40+ languages

    10Agent
  12. #1980 · Trially

    Agentic AI that enrolls clinical trials faster by converting patient matches

    10Agent
  13. #1981 · RayThera

    AI-driven small-molecule discovery for safer, more effective immunology drugs

    10Agent
  14. #1982 · GovSignals

    AI platform to find and bid on government contracts in minutes

    10Agent
  15. #1983 · Civic Roundtable

    Secure collaboration and operations platform for government workers

    10Agent
  16. #1984 · Govstream.ai

    AI-native permitting tools to help cities move faster on housing

    10Agent
  17. #1985 · Abel

    AI toolkit that automates police paperwork and report writing

    10Agent
  18. #1986 · Freeform

    AI-driven laser metal additive manufacturing at production scale

    10Agent
  19. #1987 · Overstory

    AI vegetation intelligence to prevent wildfires and grid outages

    10Agent
  20. #1988 · Tibo Energy

    AI energy management to tackle grid congestion for businesses

    10Agent
  21. #1989 · dcbel

    AI home energy station with bidirectional EV charging and solar

    10Agent
  22. AI-driven power trading and dispatch infrastructure for renewables

    10Agent
  23. #1991 · Clyx

    A social calendar for genuine friends and curated real-life events

    10Agent
  24. #1992 · Casium

    AI platform that streamlines US work visa applications for employers and immigration teams

    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.