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. #337 · Unsloth

    Open-source toolkit to fine-tune and run LLMs faster with less memory

    50Agent
    API Python
  2. #338 · Voyage AI

    State-of-the-art embedding and reranking models for accurate retrieval

    50Agent
    API PythonREST API
  3. #339 · Ollama

    The easiest way to run open LLMs locally and in the cloud

    50Agent
    API PythonJavaScript +1
  4. #340 · Sedai

    Self-driving cloud: AI agents autonomously optimize cost, performance and availability

    50Agent
    API OAuth2
  5. #341 · ZeroPath

    AI-native SAST that finds business-logic flaws and ships verified patches

    50Agent
    API OAuth2
  6. #342 · Ai2 (Allen Institute for AI)

    Paul Allen's non-profit lab building truly open models like OLMo, Molmo and Tulu

    50Agent
    API Python
  7. #343 · ByteDance

    Chinese tech giant behind TikTok, CapCut, Doubao, and Seedance AI models

    50Agent
    API OAuth2
  8. #344 · Devs.ai

    Enterprise platform to build governed AI apps on your data

    50Agent
    API OAuth2
  9. #345 · Marr Labs

    AI voice agents for regulated industries

    50Agent
    API OAuth2
  10. #346 · Modal

    High-performance AI infrastructure with sub-second cold starts and instant autoscaling.

    50Agent
    PythonJavaScript +1
  11. #347 · Novita AI

    Affordable model APIs, serverless GPUs, and agent sandboxes in one cloud

    50Agent
    API PythonJavaScript +1
  12. #348 · Kling AI

    Next-generation AI video creation

    50Agent
    API Webhooks
  13. #349 · Sentient

    Open, community-built AGI to take on closed labs

    50Agent
    API pythontypescript
  14. #350 · Confident AI

    DeepEval-powered LLM evaluation and observability

    50Agent
    API Webhooks OAuth2 pythonrest
  15. #351 · Cartesia

    Ultra-fast voice AI for real-time applications

    50Agent
    API PythonJavaScript/TypeScript
  16. #352 · Cresta

    Generative AI for the contact center

    50Agent
    API
  17. #353 · Langfuse

    Open source LLM engineering platform for debugging, analyzing, and iterating on LLM applications

    50Agent
    PythonJavaScript +1
  18. #354 · Krisp

    Voice AI for meetings with #1 noise cancellation, accent AI, translation, and AI note taker.

    50Agent
  19. #355 · LanceDB

    AI-native multimodal lakehouse for vector search, training data, and retrieval.

    50Agent
    PythonTypeScript +3
  20. #356 · Weights & Biases

    The AI developer platform

    50Agent
    API Python
  21. #357 · Kumo

    Relational foundation model for predictive AI

    50Agent
    MCP API Webhooks OAuth2 python
  22. #358 · Superlog

    AI-native observability that installs itself and ships pull requests to fix the bugs it finds.

    50Agent
    JavaScriptTypeScript
  23. #359 · Banana

    Inference hosting for AI teams who ship fast and scale faster.

    50Agent
    python
  24. #360 · Runpod

    The fastest way to deploy and scale AI workloads with on-demand GPUs and serverless infrastructure.

    50Agent
    Python

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.