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. #2017 · Freeplay

    End-to-end platform for product teams building with LLMs, covering prompt and model

    10Agent
  2. #2018 · Nory

    AI-native restaurant management platform that unifies business intelligence, workforce

    10Agent
  3. #2019 · Unique

    Zurich-based agentic AI platform built for financial services, automating middle- and

    10Agent
  4. #2020 · Fluidstack

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

    10Agent
  5. #2021 · Reflex Aerospace

    German New Space company that designs and builds custom small satellites at speed, operating a

    10Agent
  6. #2022 · Axelera AI

    Eindhoven-based semiconductor company building AI hardware for generative AI and computer

    10Agent
  7. #2023 · Tembo

    Managed Postgres platform that makes the open-source database easy to deploy and extend for

    10Agent
  8. #2024 · Aichiki

    Immersive AI character chat across web and mobile

    10Agent
  9. #2025 · RepublicLabs

    The people's generative AI playground for image and video

    10Agent
  10. #2026 · Supermaven

    The fastest code autocomplete — 1M token context, instant suggestions

    10Agent
    TypeScriptPython +1
  11. #2027 · FurtherAI

    Insurance-native AI workspace automating submissions, policy comparison, claims and compliance.

    10Agent
  12. #2028 · General Instinct

    Deploy frontier AI into any edge device, fully offline, at maximum performance.

    10Agent
  13. #2029 · ConCntric

    AI-powered preconstruction platform with agentic planning

    10Agent
  14. #2030 · Reforged Labs

    GenAI workspace for game studios to produce performance video ads

    10Agent
  15. #2031 · OnSite

    AI communication platform for the construction industry

    10Agent
  16. #2032 · Reckon.ai

    AI computer vision turning fridges and shelves into autonomous stores

    10Agent
  17. #2033 · Quanta

    AI-native accounting that builds books in real time

    10Agent
  18. #2034 · Triomics

    Oncology-specific AI agents that turn unstructured EHRs into structured cancer data

    10Agent
  19. #2035 · Poppy

    Proactive AI assistant that organizes your digital life from calendar to messages

    10Agent
  20. #2036 · Fermata

    Computer vision AI for early pest and disease detection in greenhouse crops

    10Agent
  21. #2037 · Meshed

    AI voice agents and automation for insurance broking

    10Agent
  22. #2038 · Nabla Bio

    Generative AI for de novo antibody and protein design against tough drug targets

    10Agent
  23. #2039 · Tutor Intelligence

    Central robot intelligence powering fleets of warehouse robot workers

    10Agent
  24. #2040 · Edumentors

    Online tutoring with top UK university tutors and an AI tutor

    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.