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

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #1681 · Comp AI

    Open-source, AI-powered compliance automation platform that helps companies achieve and

    10Agent
  2. #1682 · Ravenna

    AI-native internal service desk built directly inside Slack that automates IT, HR, and

    10Agent
  3. #1683 · Theseus

    GPS-denied navigation for military drones

    10Agent
  4. #1684 · Cekura

    (formerly Vocera) is a testing and observability platform for AI voice and chat agents

    10Agent
  5. #1685 · Telli

    Berlin-based platform for AI voice agents that automate high-volume business phone calls, with

    10Agent
  6. #1686 · Wittify.ai

    Saudi conversational-AI startup building Arabic-native AI agents that listen, act, and

    10Agent
  7. #1687 · Kilow

    Saudi digital-health startup offering an Arabic-first, medically supervised weight-management

    10Agent
  8. #1688 · Tobiko Data

    SQLMesh and SQLGlot, modern open-source tools for data transformation that bring virtual data

    10Agent
  9. #1689 · Topo

    Autonomous AI sales development representatives (SDRs) that automate outbound prospecting for

    10Agent
  10. #1690 · Qevlar AI

    Paris-based agentic AI security operations platform that autonomously enriches, correlates

    10Agent
  11. #1691 · Strawberry

    Stockholm-based startup building an agentic AI browser that lets knowledge workers automate

    10Agent
  12. #1692 · Gumloop

    No-code platform for building AI agents and automating workflows using a drag-and-drop visual

    10Agent
  13. #1693 · Tektonic AI

    GenAI agents that automate complex enterprise business operations, starting with sales and

    10Agent
  14. #1694 · Capsule Security

    Provides a runtime trust layer for agentic AI, monitoring and controlling AI agents as they

    10Agent
  15. #1695 · Treefera

    Uses satellite imagery and AI to map the 'first mile' of nature-based supply chains, tracking

    10Agent
  16. #1696 · AMP Robotics

    AI-powered robotics and vision systems that automate the sorting of recyclables in materials

    10Agent
  17. #1697 · Altera

    Applied research company building autonomous, socially intelligent AI agents it calls digital

    10Agent
  18. #1698 · SPARQ

    AI-native game engine and creator platform built on a proprietary C++ engine with AAA-grade

    10Agent
  19. #1699 · Tabs

    AI-native revenue platform for B2B finance and accounting teams that automates the entire

    10Agent
  20. #1700 · Truveta

    Health data and analytics company built by a collective of US health systems to enable

    10Agent
  21. #1701 · pyannoteAI

    Paris-based company building a language-agnostic speaker intelligence platform

    10Agent
  22. #1702 · Simple AI

    Voice AI agents for direct-to-consumer sales and support, designed to convert and upsell on

    10Agent
  23. #1703 · Bluebook

    Stockholm-based AI platform building "self-driving accounting" for accounting firms

    10Agent
  24. #1704 · Fluidstack

    London-based AI cloud platform providing large-scale GPU compute for training and inference

    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.