 Claude models with tool use, the MCP connector, Agent Skills, and the Claude Agent SDK OpenAPI | llm+5 | OpenAPI | MPP | api-key, Models | 5/5 | | |
 Marketplace of thousands of scraping and automation Actors, exposed over API and a remote MCP server MCPOpenAPIllms.txt | scraping+4 | MCP+2 | — | api-key, Browsers | 5/5 | | |
 OpenTelemetry-native, open-source tracing and evaluation for LLM and agent applications MCPOpenAPIllms.txt | observability+3 | MCP+2 | — | api-key, Observability | 5/5 | | |
 Eval-first platform — datasets, scorers, CI gating, and logging for agent changes MCPOpenAPIllms.txt | evals+3 | MCP+2 | — | api-key, Observability | 5/5 | | |
 Independent web index with news, images, and AI-grounding endpoints MCPOpenAPI | search+3 | MCP+1 | — | api-key, Search | 5/5 | | |
 Cloud browser infrastructure for agents, with Stagehand, session recording, and pay-per-session MPP billing MCPOpenAPIllms.txt | browser+4 | MCP+2 | MPP | api-key, Browsers | 5/5 | | |
 Open-source embedding database with Chroma Cloud and an official MCP server MCPOpenAPIllms.txt | vector-db+3 | MCP+2 | — | api-key, Memory | 5/5 | | |
 Framework for durable agents on Workers, with built-in payment support across x402 and the Visa and Mastercard agent schemes MCPOpenAPIllms.txt | agents+5 | MCP+2 | Agent Pay+2 | api-key, Platforms | 5/5 | | |
 Edge compute with Durable Objects, Agents SDK, containers, and x402 payment support MCPOpenAPIllms.txt | serverless+4 | MCP+2 | x402 | api-key, Compute | 5/5 | | |
 Run models at the edge from Workers, with an OpenAI-compatible endpoint and AI Gateway MCPOpenAPIllms.txt | llm+3 | MCP+2 | — | api-key, Models | 5/5 | | |
 Open-source memory engine that builds a queryable knowledge graph from documents, code, and conversations MCPOpenAPIllms.txt | agent-memory+3 | MCP+2 | — | api-key, Memory | 5/5 | | |
 Managed auth plus hundreds of app integrations, exposed to agents through the Rube MCP server MCPOpenAPIllms.txt | tools+3 | MCP+2 | — | api-key, Platforms | 5/5 | | |
 Sandboxes for AI agents with sub-100ms creation, snapshots, and a declarative image builder MCPOpenAPIllms.txt | sandbox+3 | MCP+2 | — | api-key, Compute | 5/5 | | |
 Secure code-execution sandboxes for agents, with persistent filesystems and sub-second starts MCPOpenAPIllms.txt | code-execution+3 | MCP+2 | — | api-key, Compute | 5/5 | | |
 Text-to-speech, voice cloning, dubbing, and an official MCP server over the audio platform MCPOpenAPIllms.txt | tts+3 | MCP+2 | — | api-key, Speech | 5/5 | | |
 Neural web search, contents, and research endpoints for agents, with a hosted MCP server MCPOpenAPIllms.txt | search+4 | MCP+2 | — | api-key, Search | 5/5 | | |
 Fast image, video, and audio generation on serverless GPUs with a queue API and webhooks OpenAPIllms.txt | image+3 | OpenAPI+1 | — | api-key, Media | 5/5 | | |
 Scrape, crawl, map, and search the web into clean markdown or JSON, with a hosted MCP server MCPOpenAPIllms.txt | scraping+4 | MCP+2 | — | api-key, Browsers | 5/5 | | |
 Gemini multimodal models via Google AI Studio and Vertex AI, with function calling and MCP support OpenAPI | llm+3 | OpenAPI | MPP | api-key, Models | 5/5 | | |
 Serverless and dedicated inference for open models, plus a hosted MCP endpoint over Hub tools MCPOpenAPI | llm+3 | MCP+1 | — | api-key, Models | 5/5 | | |