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.
Filter tools
Filters
Showing 24 of 2662 tools.
Ranked tools
-
-
-
- 10Agent#1900 · SwarmFarm Robotics
Lightweight autonomous farm robots that work in coordinated fleets
- 10Agent#1901 · Mantel Capture
MIT spinout developing low-cost, energy-efficient carbon capture for heavy industry using a
- 10Agent#1902 · Cartwheel
AI-powered 3D character animation platform that lets creators generate production-ready
- 10Agent#1903 · GameRamp
AI-native publishing and live-ops operating system built for mobile games and consumer apps
- 10Agent#1904 · USD.AI
Stablecoin lending protocol that provides credit to AI infrastructure companies using GPUs and
- 10Agent#1905 · Logic
AI-powered decision automation platform that lets business teams automate recurring review and
- 10Agent#1906 · AirOps
AI content engineering platform that helps marketing teams build, optimize, and scale SEO and
- 10Agent#1907 · Octolane
AI-native, self-driving CRM that automates sales actions, follow-ups, and record updates
- 10Agent#1908 · Viktor
AI 'coworker' that lives inside Slack and Microsoft Teams and actually completes work rather
- 10Agent#1909 · Charlie Labs
Charlie, an autonomous AI software engineer focused on TypeScript that reviews code, fixes
- 10Agent#1910 · CoPlane
AI-native back-office platform that wraps automation around legacy ERP systems for essential
- 10Agent#1911 · Traza
AI workers that automate administrative procurement and supply-chain operations for enterprise
-
-
- 10Agent#1914 · Portal Space Systems
Rapidly maneuverable spacecraft powered by solar-thermal propulsion
- 10Agent#1915 · Hamming AI
Enterprise platform for testing, monitoring, and governing AI voice agents before and after
- 10Agent#1916 · Neuphonic
London-based voice AI company building ultra-low-latency, multilingual text-to-speech and
- 10Agent#1917 · Vocca
AI voice agents that automate the front desk of medical and dental practices, answering
- 10Agent#1918 · Reve
AI image generation and editing company building models known for strong prompt adherence
- 10Agent#1919 · BetterPic
AI imaging platform that generates professional headshots and portraits from everyday selfies
- 10Agent#1920 · Amini
Nairobi-based climate-tech and data-infrastructure company using AI and satellite technology
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.