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. #481 · Nekuda

    Payment infrastructure and secure SDK built for AI agents to transact on a user's behalf

    40Agent
    API
  2. #482 · SolvaPay

    Machine-native payment rails letting AI agents discover, access and pay for digital services

    40Agent
    API
  3. #483 · Cognee

    Open-source memory engine that turns scattered data into a knowledge graph for AI agents

    40Agent
    API
  4. #484 · Euno

    Data model governance that pulls business logic out of BI tools and back into the data layer

    40Agent
    API
  5. #485 · Sim

    Open-source AI workspace where teams build, deploy and manage AI agents

    40Agent
    API
  6. #486 · Claap

    AI sales intelligence that records calls and auto-fills your CRM

    40Agent
    API
  7. #487 · Vida

    AI agent OS for phone and messaging with carrier-grade telecom built in

    40Agent
    API
  8. #488 · OpenEvidence

    AI medical assistant for clinicians

    40Agent
    API TypeScriptPython
  9. #489 · Alaan

    AI-powered spend management and corporate cards for MENA finance teams

    40Agent
    API
  10. #490 · Windsurf

    Agentic AI IDE for next-generation coding.

    40Agent
    PythonJavaScript +1
  11. #491 · Sentra

    Cloud-native data security for the AI era

    40Agent
    API
  12. #492 · Harmonic

    Mathematical superintelligence with hallucination-free, verified reasoning

    40Agent
    API
  13. #493 · OpusClip

    Turn long videos into viral short clips with AI

    40Agent
    API
  14. #494 · Perceptron AI

    Foundation models for real-time multimodal intelligence in the physical world

    40Agent
    API
  15. #495 · Precip

    High-precision AI weather models

    40Agent
    API
  16. #496 · Pixelcut

    AI photo and product-image editor used by 70M+ creators, from cutouts to AI video

    40Agent
    API
  17. #497 · Exaforce

    Agentic SOC platform for real-time threat detection and response

    40Agent
    API
  18. #498 · Dexory

    Autonomous robots and AI that turn warehouses into real-time digital twins

    40Agent
    API
  19. #499 · Oasis Security

    Agentic access management to secure AI agents and non-human identities

    40Agent
    API
  20. #500 · Augury

    AI-driven machine health and production health for industrial reliability

    40Agent
    API
  21. #501 · Qualified Health

    Enterprise generative AI infrastructure and governance for health systems

    40Agent
    API
  22. #502 · Mytra

    3D robotic operating system for supply chain and warehouse storage

    40Agent
    API
  23. #503 · Moosend

    Affordable email marketing and automation platform

    40Agent
    API
  24. #504 · Freepik

    AI-powered platform for images, video, icons and design assets

    40Agent
    API

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.