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. #1993 · CaseBlink

    AI platform for immigration law firms that automates end-to-end case preparation, from intake

    10Agent
  2. #1994 · AttiFin AI

    UK legal-AI startup building an enterprise platform trained specifically on UK and devolved law

    10Agent
  3. #1995 · Spiritus

    Carbon removal company developing low-cost direct air capture (DAC) technology to pull carbon

    10Agent
  4. #1996 · Backflip

    AI 3D modeling platform that turns text prompts and images into high-resolution, game- and

    10Agent
  5. #1997 · Warmly

    AI-powered signal-based revenue orchestration platform that helps B2B sales and marketing

    10Agent
  6. #1998 · Atlan

    Modern data catalog and active metadata platform that helps enterprises discover, govern, and

    10Agent
  7. #1999 · Cernel

    Danish AI startup building the infrastructure for agentic commerce

    10Agent
  8. #2000 · Senra Systems

    Software-defined wire harness manufacturing for aerospace and defense

    10Agent
  9. #2001 · Thoughtly

    No-code platform for building human-like AI voice agents for contact centers and revenue teams

    10Agent
  10. #2002 · Elevify

    Brazilian edtech building an AI-powered education marketplace that organizes existing online

    10Agent
  11. #2003 · SehaTech

    Egyptian insurtech using AI to automate health-insurance operations across the MENA region

    10Agent
  12. #2004 · Sigma Computing

    Cloud-native business intelligence and analytics platform that lets anyone explore live data

    10Agent
  13. #2005 · Gable

    Data governance and lineage platform built around data contracts, agreements between the

    10Agent
  14. #2006 · Teacher's Buddy

    AI-powered workspace built to fight teacher burnout by cutting administrative work, supporting

    10Agent
  15. #2007 · Jeeva AI

    Multi-agent sales automation platform that deploys autonomous AI digital workers across

    10Agent
  16. #2008 · OpenFunnel

    Personalized AI agents that monitor a company's total addressable market and surface in-market

    10Agent
  17. #2009 · Rippletide

    Paris-based startup building AI agents for sales, including an AI sales copilot that automates

    10Agent
  18. #2010 · Linkerbot

    Beijing-based company that designs and mass-produces high-degree-of-freedom dexterous robotic

    10Agent
  19. #2011 · Spun

    Jakarta-based startup building AI-enabled visa infrastructure that treats visas as core travel

    10Agent
  20. #2012 · uiAgent

    Provides an AI-agent automation platform for accounting firms, delivered through its product

    10Agent
  21. #2013 · Sherpas

    AI-native infrastructure platform for wealth management firms that standardizes how financial

    10Agent
  22. #2014 · Sully.ai

    Autonomous AI agents, or AI medical employees, that automate clinical and administrative work

    10Agent
  23. #2015 · Valar Labs

    AI-powered precision oncology tests that predict how individual cancer patients will respond

    10Agent
  24. #2016 · VoiceCare AI

    Agentic voice AI to automate complex back-office phone conversations in healthcare, such as

    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.