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

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #2161 · Bitpart AI

    Provides game developers with pre-trained, AI-driven non-player characters that can hold

    10Agent
  2. #2162 · Sedric AI

    Compliance platform built specifically for regulated financial services, powered by the first

    10Agent
  3. #2163 · Persana AI

    Prospecting superapp that uses AI agents and multi-source data to automate go-to-market lead

    10Agent
  4. #2164 · Aomni

    AI agent platform for revenue teams that automates account research, sales preparation, and

    10Agent
  5. #2165 · etalytics

    German deep-tech company that uses AI to optimize energy systems in industry and data centers

    10Agent
  6. #2166 · Antithesis

    Autonomous software testing platform built on deterministic simulation testing, which runs

    10Agent
  7. #2167 · Corgea

    AI-powered application security platform that automatically scans source code, finds and

    10Agent
  8. #2168 · Moderne

    Automates large-scale code refactoring, migration, and modernization across massive enterprise

    10Agent
  9. #2169 · Numra

    AI agents for finance operations, led by its AI finance assistant 'Mary' that automates

    10Agent
  10. Automates the high-volume, repetitive phone calls that run the back office of US healthcare

    10Agent
  11. #2171 · PlayAI

    (formerly PlayHT) is a voice AI platform offering generative text-to-speech models and a

    10Agent
  12. #2172 · Metaplane

    Data observability platform that uses machine learning to automatically detect anomalies

    10Agent
  13. #2173 · Coalesce

    Data transformation platform purpose-built for Snowflake that combines a visual, column-aware

    10Agent
  14. #2174 · Lumi AI

    Agentic enterprise analytics platform that connects to databases, warehouses, and ERP systems

    10Agent
  15. #2175 · Validio

    Agentic data management platform that automates data quality, observability, lineage, and

    10Agent
  16. #2176 · Super Teacher

    AI-powered tutoring app for elementary school students that delivers conversational

    10Agent
  17. #2177 · Subject

    Provides AI-powered digital curriculum and online learning for grades 6-12, combining

    10Agent
  18. #2178 · SpeakX

    AI-powered English-speaking platform that helps learners build spoken fluency through short

    10Agent
  19. #2179 · RevisionDojo

    AI-first exam-prep platform for high-stakes exams like the International Baccalaureate (IB)

    10Agent
  20. #2180 · trumpet

    Digital sales room platform that gives B2B buyers and sellers a single personalized

    10Agent
  21. #2181 · Midpage

    AI-powered legal research and drafting platform that gives AI direct access to real case law

    10Agent
  22. #2182 · Pragma

    Backend game engine that powers live-service games, handling matchmaking, analytics

    10Agent
  23. #2183 · Regal AI

    New York-based platform that builds AI phone agents for enterprise contact centers, handling

    10Agent
  24. #2184 · Vodex

    Generative-AI voice platform that automates outbound business calls with human-like AI agents

    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.