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. #361 · deepset

    Haystack framework and deepset Cloud for enterprise LLM apps

    50Agent
    API Webhooks OAuth2 pythonrest
  2. #362 · Limrun

    Cloud XCode, iOS and Android simulators that let any coding agent build mobile apps without a Mac.

    50Agent
    CLI
  3. #363 · FlexAI

    AI infrastructure that adapts as you grow, orchestrating across any cloud or hardware for faster deployment and optimal cost-performance.

    50Agent
    Python
  4. #364 · ZenML

    The AI Control Plane for unifying ML and GenAI workflows across your fragmented stack.

    50Agent
    Python
  5. #365 · FuriosaAI

    Powerfully efficient AI inference for enterprise and cloud with high-performance LLM and multimodal deployment capabilities.

    50Agent
    Python
  6. #366 · Comet

    The AI Developer Platform for building, debugging, and deploying reliable AI agents.

    50Agent
  7. #367 · MOSTLY AI

    Unlock the power of data with a platform for secure access, high-quality synthetic data generation, and seamless data analysis.

    50Agent
    Python
  8. #368 · Convai

    Craft and deploy spatially 3D-aware conversational AI characters for virtual worlds and immersive experiences.

    50Agent
  9. #369 · Sanas

    The real-time speech AI platform making conversations clear, natural, and scalable for the modern world.

    50Agent
  10. #370 · Lorikeet

    The AI Customer Concierge for complex companies, resolving customer problems end-to-end across their lifecycle.

    50Agent
  11. #371 · Substrate

    The platform for agentic AI, providing infrastructure for intelligent software with elegant abstractions and high-performance components.

    50Agent
    PythonTypeScript
  12. #372 · Rev

    #1 speech-to-text service for lawyers and beyond, combining human and AI transcription.

    49Agent
    API Webhooks rubypython +1
  13. #373 · Zhipu AI

    Chinese foundation model lab behind ChatGLM and GLM-4.

    48Agent
    API PythonGo
  14. #374 · Kalshi

    The first US-regulated prediction market exchange

    48Agent
    API
  15. Wafer-scale AI chips for unprecedented speed

    48Agent
    API PythonNode.js
  16. #376 · Tenstorrent

    Tenstorrent provides high-performance AI compute solutions, from cards and workstations to scale-out servers, powered by flexible, open-source IP.

    47Agent
    API Python
  17. #377 · Moonshot AI

    Maker of Kimi — the long-context AI chatbot.

    45Agent
    API pythonjavascript
  18. #378 · Liquid AI

    Efficient general-purpose foundation models built for edge, on-device, and cloud deployment at every scale.

    45Agent
    Python
  19. #379 · Decagon

    AI agents that actually solve customer problems

    45Agent
    API
  20. #380 · Niantic Labs

    Niantic creates real-world augmented reality games and apps that encourage exploration and social interaction.

    45Agent
    UnityC# +2
  21. #381 · Tines

    The intelligent workflow platform to securely scale AI and automation, integrating agents, teams, and tools with speed and control.

    45Agent
  22. #382 · Dust

    Deploy, orchestrate, and govern fleets of specialized AI agents safely connected to your company's knowledge and tools.

    45Agent
  23. #383 · Paradox

    Conversational AI hiring software that automates tasks and streamlines the entire recruitment process.

    45Agent
  24. #384 · Parloa

    An AI Agent Management Platform that transforms customer conversations into lasting loyalty for contact centers.

    45Agent

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.