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. #1537 · Xpanner

    Automation-as-a-Service that retrofits construction equipment with autonomous AI

    10Agent
  2. #1538 · Unlimited Industries

    AI-native construction company for energy and data center infrastructure

    10Agent
  3. #1539 · Kana

    Flexible AI agents for marketing operations and campaign execution

    10Agent
  4. #1540 · Dazzle

    An AI personal assistant from former Yahoo CEO Marissa Mayer

    10Agent
  5. #1541 · Solve Intelligence

    AI copilot for patents, drafting, prosecution and litigation for IP teams worldwide.

    10Agent
  6. #1542 · AIUC

    Insurance, audits and certification for AI agents

    10Agent
  7. #1543 · Basecamp Research

    Building a GPT for biology from the planet's largest proprietary genomic dataset

    10Agent
  8. #1544 · Luca

    AI-powered K-12 learning platform for Latin American schools

    10Agent
  9. #1545 · Vimi

    Personalized AI math tutor for K-12 students, built for the curriculum

    10Agent
  10. #1546 · Freed

    AI clinician assistant that writes your notes so you can focus on patients

    10Agent
  11. #1547 · FLORA

    An infinite canvas that unifies every creative AI tool into one workflow

    10Agent
  12. #1548 · Leo AI

    The first generative AI copilot built for mechanical engineering and CAD

    10Agent
  13. #1549 · FieldAI

    Physics-first foundation models that are universal brains for robots

    10Agent
  14. #1550 · Series

    The first AI social network that lives entirely inside iMessage

    10Agent
  15. #1551 · Born

    Social AI companions and virtual pets that combat loneliness

    10Agent
  16. #1552 · Wabi

    The YouTube of apps: prompt to instantly build and share mini-apps

    10Agent
  17. #1553 · FleetWorks

    An always-on AI dispatcher that matches trucks with freight

    10Agent
  18. #1554 · Apoha

    AI for molecular behavior — the next data class after sequence and structure

    10Agent
  19. #1555 · Ankar

    AI platform that streamlines how companies and law firms capture, file and manage patents

    10Agent
  20. #1556 · Brightband

    AI weather and climate forecasting company building an end-to-end Earth System model trained

    10Agent
  21. #1557 · Silurian

    Earth intelligence company building foundation models to simulate the planet, starting with

    10Agent
  22. #1558 · Odyssey

    AI research lab building world models that generate and stream interactive 3D environments in

    10Agent
  23. #1559 · Lyzr

    Enterprise agentic AI platform that lets companies build, deploy, and govern autonomous AI

    10Agent
  24. #1560 · DualEntry

    AI-native ERP platform built for the mid-market that automates up to 90% of manual accounting

    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.