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. #2065 · RobCo

    Munich-based industrial robotics company that makes modular, easy-to-configure robots for

    10Agent
  2. #2066 · AgriPass Robotics

    Israeli agritech startup building AI-driven robotic weeding technology for farmers

    10Agent
  3. #2067 · Ringg AI

    Bengaluru-based voice AI platform that lets companies run operations as natural, multilingual

    10Agent
  4. #2068 · Seezo

    Bengaluru-based cybersecurity startup offering GenAI-powered automated security design reviews

    10Agent
  5. #2069 · Vibrium

    Gurugram-based enterprise agentic AI startup building an outcome-driven, goal-oriented AI

    10Agent
  6. #2070 · Eleos Health

    Behavioral health AI company that automates clinical documentation and surfaces care insights

    10Agent
  7. #2071 · Candid Health

    Revenue cycle automation platform that simplifies and streamlines medical billing for

    10Agent
  8. #2072 · Rilla

    Voice AI platform that records, transcribes, and analyzes in-person sales and service

    10Agent
  9. #2073 · Athina AI

    Evaluation and monitoring platform that helps developers prototype, experiment with, evaluate

    10Agent
  10. #2074 · Kobalt Labs

    AI copilot for risk and compliance teams at banks, fintechs and financial institutions

    10Agent
  11. #2075 · Doubleword

    Doubleword, formerly TitanML, is a London-based company building a unified self-hosted

    10Agent
  12. #2076 · MetalBear

    Company behind mirrord, an open-source tool that lets developers connect local code directly

    10Agent
  13. #2077 · kapa.ai

    AI assistants that answer technical product and developer questions using a company's own

    10Agent
  14. #2078 · Quack

    Proactive, agentic AI platform for customer support that aims to identify and resolve customer

    10Agent
  15. #2079 · FantasyAI.world

    Free, anonymous, uncensored AI roleplay chatbot

    10Agent
  16. #2080 · Observe.AI

    AI intelligence for the contact centre

    10Agent
    API
  17. #2081 · Resemble AI

    Generative voice AI with deepfake detection

    10Agent
    API PythonNode.js +1
  18. #2082 · Continue

    Quality control for your software factory with AI checks on every pull request.

    10Agent
    TypeScript
  19. #2083 · tl;dv

    AI meeting notetaker for Zoom, Google Meet, and Teams

    10Agent
    API Webhooks OAuth2 rest
  20. #2084 · Kili Technology

    Enterprise data labeling and annotation for AI teams

    10Agent
    API Webhooks OAuth2 pythonrest
  21. #2085 · Astraea

    Agents that compress clinical trial biometrics from months to days.

    10Agent
  22. #2086 · Manicule

    AI-native documentation studio for developer tool companies.

    10Agent
  23. #2087 · Degla

    Fully autonomous intelligence layer in the sky for multi-drone missions.

    10Agent
  24. #2088 · Voquill

    Realtime AI scribe that helps pathologists work cases faster.

    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.