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
- API Webhooks OAuth2 pythonrest
- 50Agent#362 · Limrun
Cloud XCode, iOS and Android simulators that let any coding agent build mobile apps without a Mac.
CLI - 50Agent#363 · FlexAI
AI infrastructure that adapts as you grow, orchestrating across any cloud or hardware for faster deployment and optimal cost-performance.
Python - 50Agent#364 · ZenML
The AI Control Plane for unifying ML and GenAI workflows across your fragmented stack.
Python - 50Agent#365 · FuriosaAI
Powerfully efficient AI inference for enterprise and cloud with high-performance LLM and multimodal deployment capabilities.
Python - 50Agent#366 · Comet
The AI Developer Platform for building, debugging, and deploying reliable AI agents.
- 50Agent#367 · MOSTLY AI
Unlock the power of data with a platform for secure access, high-quality synthetic data generation, and seamless data analysis.
Python - 50Agent#368 · Convai
Craft and deploy spatially 3D-aware conversational AI characters for virtual worlds and immersive experiences.
- 50Agent#369 · Sanas
The real-time speech AI platform making conversations clear, natural, and scalable for the modern world.
- 50Agent#370 · Lorikeet
The AI Customer Concierge for complex companies, resolving customer problems end-to-end across their lifecycle.
- 50Agent#371 · Substrate
The platform for agentic AI, providing infrastructure for intelligent software with elegant abstractions and high-performance components.
PythonTypeScript - 49Agent#372 · Rev
#1 speech-to-text service for lawyers and beyond, combining human and AI transcription.
API Webhooks rubypython +1 - API PythonGo
- API
- API PythonNode.js
- 47Agent#376 · Tenstorrent
Tenstorrent provides high-performance AI compute solutions, from cards and workstations to scale-out servers, powered by flexible, open-source IP.
API Python - API pythonjavascript
- 45Agent#378 · Liquid AI
Efficient general-purpose foundation models built for edge, on-device, and cloud deployment at every scale.
Python - API
- 45Agent#380 · Niantic Labs
Niantic creates real-world augmented reality games and apps that encourage exploration and social interaction.
UnityC# +2 - 45Agent#381 · Tines
The intelligent workflow platform to securely scale AI and automation, integrating agents, teams, and tools with speed and control.
- 45Agent#382 · Dust
Deploy, orchestrate, and govern fleets of specialized AI agents safely connected to your company's knowledge and tools.
- 45Agent#383 · Paradox
Conversational AI hiring software that automates tasks and streamlines the entire recruitment process.
- 45Agent#384 · Parloa
An AI Agent Management Platform that transforms customer conversations into lasting loyalty for contact centers.
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.