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. #1321 · Black Forest Labs

    Frontier AI research lab for visual intelligence, building production-grade image generation and editing models.

    10Agent
    API
  2. #1322 · Nirvana Insurance

    AI-powered commercial trucking insurance

    10Agent
    API Webhooks rest
  3. #1323 · Physical Intelligence

    Foundation models for physical world AI

    10Agent
    API Python
  4. #1324 · Ema

    Universal AI employee for the enterprise

    10Agent
    API Webhooks OAuth2 pythontypescript
  5. #1325 · 7AI

    Agentic cybersecurity platform deploying autonomous AI security agents for alert triage and investigation.

    10Agent
  6. #1326 · Generalist AI

    General-purpose embodied foundation models for physical-world robots

    10Agent
  7. #1327 · Armadin

    Autonomous AI red-teaming for the era of AI hyperattacks

    10Agent
  8. #1328 · Paradigm Health

    AI research platform making clinical trials part of routine patient care

    10Agent
  9. #1329 · Peregrine Technologies

    Decision-support and data integration platform for public safety agencies

    10Agent
  10. #1330 · Blue Water Autonomy

    Building the world's most capable fully autonomous warships

    10Agent
  11. #1331 · Unconventional AI

    Reinventing the computer with brain-inspired, energy-efficient AI hardware

    10Agent
  12. #1332 · Decagon

    AI agents that actually solve customer problems

    10Agent
    API
  13. #1333 · Periodic Labs

    Creating AI scientists and autonomous laboratories to accelerate scientific discovery, starting with physical sciences.

    10Agent
  14. #1334 · Plaud AI

    AI voice recorder devices for hands-free note-taking

    10Agent
  15. #1335 · Monaco

    AI-native sales engine pairing AI agents with human sales experts for startups

    10Agent
  16. #1336 · Augment

    AI teammate that automates freight order-to-cash workflows

    10Agent
  17. #1337 · HavocAI

    Collaborative maritime autonomy for fleets of uncrewed surface vessels

    10Agent
  18. #1338 · Model ML

    AI workspace that automates investment banking and finance workflows

    10Agent
  19. #1339 · OpenEvidence

    AI medical assistant for clinicians

    10Agent
    API TypeScriptPython
  20. #1340 · Nous Research

    Open-source AI lab building decentralized models, agents, and training

    10Agent
    API pythontypescript
  21. #1341 · TensorWave

    AI cloud built on AMD Instinct accelerators, operating one of the world's largest liquid-cooled AMD GPU deployments.

    10Agent
  22. #1342 · Quobly

    Industrial silicon-based quantum computers built on semiconductor fabs.

    10Agent
  23. #1343 · ZyG

    An agentic operating system that scales DTC ecommerce brands end to end

    10Agent
  24. #1344 · Praktika

    AI avatar tutors for natural, conversational language learning

    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.