Manage serverless cloud functions on Google Cloud. Create, update, deploy, list, and delete functions triggered by HTTP requests or cloud events. Configure runtimes (Node.js, Python, Go, Java, .NET, Ruby), event triggers (Cloud Storage, Pub/Sub, Firestore), memory, timeouts, and environment variables. Upload and download function source code via signed URLs. Invoke deployed HTTP functions. Manage function upgrades from 1st gen to 2nd gen. List available runtimes and monitor long-running deployment operations. Configure ingress/egress networking, secret environment variables, and authentication settings for function invocation.

Generate text and analyze images using Claude language models. Send conversational messages with configurable parameters (model, temperature, system prompt) and receive AI-generated responses, with optional streaming. Execute Python code in a sandboxed environment for data analysis and visualizations. Perform web searches for up-to-date information with cited sources. Use tool calling (function calling) to let Claude invoke structured tools during conversations. Enable extended thinking for complex reasoning tasks. Process and analyze images via vision capabilities. Upload and manage files for multi-session analysis. Connect to remote MCP servers for external system integration. Use agent skills for working with PowerPoint, Excel, Word, and PDF files. Count tokens, cache prompts for reduced latency and cost, create message batches for async processing, and enable citations for source attribution. Administer organizations by managing members, workspaces, invites, API keys, and retrieving usage and cost reports.

Generate text, chat responses, and structured outputs using Google's multimodal Gemini AI models. Process and understand mixed inputs including text, images, audio, video, and PDF documents. Generate images via Imagen and native models, generate videos via Veo, and create music with granular creative controls. Execute Python code within the model environment. Produce text, image, video, and audio embeddings for semantic search and classification. Upload and manage files for use in prompts. Fine-tune models with custom training data. Use built-in tools including Google Search grounding, URL context fetching, and computer use automation. Cache context for repeated use across requests. Count tokens before sending requests. Stream real-time voice and video interactions via the Live API over WebSockets. Call external functions and chain multiple tool invocations to fulfill complex requests.

Manage and interact with Appsmith, an open-source low-code platform for building internal tools and dashboards. Trigger workflow automations via webhook URLs, monitor instance health, and manage applications and workspaces. Import and export applications as JSON, connect to datasources, embed apps in external sites, and retrieve audit logs. Note: most management operations rely on internal session-based APIs rather than a formally documented public API, so programmatic capabilities are limited. Key actions include triggering workflows with HTTP POST requests, checking instance health status, exporting and importing applications, managing workspace users and roles, and querying audit logs for user and application events.

Automate headless Chrome/Chromium browsers in the cloud for web scraping, content extraction, and browser automation tasks. Scrape structured data from web pages using CSS selectors, retrieve fully rendered HTML after JavaScript execution, generate PDFs from URLs or raw HTML, capture screenshots in JPEG or PNG, download files triggered by browser interactions, and execute custom Puppeteer code for multi-step workflows. Perform web searches with optional result scraping returning LLM-ready markdown or HTML. Unblock protected websites and bypass bot detection using stealth mode and CAPTCHA solving via BrowserQL. Run Lighthouse performance audits, record browser sessions as video, and manage persistent browser sessions with configurable TTL. Supports residential proxy routing for geo-targeted requests.

Generate chat completions, embeddings, and structured outputs using Mistral AI's language models. Process documents with OCR to extract text, tables, and images from PDFs. Transcribe audio with speaker diarization. Generate code with specialized coding models. Create and manage AI agents with built-in connectors for code execution, web search, image generation, and document retrieval. Moderate content for safety across multiple languages. Fine-tune models by uploading training data and managing fine-tuning jobs. Generate text embeddings for semantic search and RAG. Perform batch inference for async bulk processing. Manage files and list available models.