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
2668
With MCP
101
Public API
642
OAuth2
133
Avg score
22.9
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #49 · You.com

    The productivity search engine with AI agents.

    76Agent
    MCP API python
  2. #50 · Hugging Face

    The AI community building the future of machine learning.

    75Agent
    PythonJavaScript
  3. #51 · Notion AI

    Connected AI workspace

    75Agent
    API JavaScript
  4. #52 · xAI

    AI designed to understand the universe

    75Agent
    MCP API
  5. #53 · Peec AI

    AI search analytics to monitor brand visibility across ChatGPT, Perplexity and Gemini

    75Agent
    MCP API
  6. #54 · Pinecone

    The vector database for AI

    75Agent
    MCP API pythontypescript
  7. #55 · 8Flow

    Workflow intelligence that surfaces ranked AI agent opportunities

    75Agent
    MCP API
  8. #56 · Octave

    The context layer powering agentic go-to-market teams

    75Agent
    MCP API
  9. #57 · Knostic

    Need-to-know access controls and security for enterprise AI

    75Agent
    MCP API
  10. #58 · Scenario

    Creative AI infrastructure for generating game-ready art assets at scale

    75Agent
    MCP API
  11. #59 · Daytona

    Secure, elastic sandbox infrastructure for running AI-generated code

    75Agent
    MCP API PythonTypeScript +1
  12. #60 · Weaviate

    Open-source AI-native vector database

    75Agent
    MCP API pythontypescript
  13. #61 · Mirakl

    AI-powered marketplace and ecommerce platform for enterprise

    75Agent
    API Webhooks OAuth2 PHP
  14. #62 · Airwallex

    Global payments and financial infrastructure for modern businesses

    75Agent
    API Webhooks OAuth2 JavaScriptPython +3
  15. #63 · Contentsquare

    The all-in-one experience intelligence platform

    75Agent
    API Webhooks OAuth2 JavaScriptiOS +1
  16. #64 · LM Studio

    The desktop app for discovering and running open LLMs locally and privately

    75Agent
    MCP API PythonJavaScript
  17. #65 · Aircall

    Cloud-based phone system and AI conversation intelligence for sales and support teams

    75Agent
    API Webhooks OAuth2 JavaScript
  18. #66 · Pipedrive

    Sales-focused CRM with an AI Sales Assistant for deal predictions and automation

    75Agent
    API Webhooks OAuth2 PHPNode.js
  19. #67 · Tigris Data

    Globally distributed, S3-compatible object storage built for AI

    75Agent
    MCP API JavaScriptPython +1
  20. #68 · Agno

    High-performance Python framework and runtime for multi-agent systems

    75Agent
    MCP API Python
  21. #69 · Sendcloud

    All-in-one shipping platform for e-commerce

    75Agent
    API Webhooks OAuth2 PHPPython +1
  22. #70 · Labelbox

    RL data engine and human expertise platform for training frontier AI

    75Agent
    API Webhooks OAuth2 Python
  23. #71 · Jina AI

    Search foundation models: embeddings, rerankers, and a web reader API

    75Agent
    MCP API PythonJavaScript +1
  24. #72 · Mixedbread

    Multimodal retrieval and search platform for AI agents

    75Agent
    MCP API PythonTypeScript +1

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.