Skip to content
AI & MLReal-timeUpdated May 2026

Anthropic

Claude, Skills, and Computer Use in every workflow

Anthropic on Tiny Command exposes Claude as a set of agentic primitives, not just a chat endpoint. Create Message and Create Message with Tools handle the standard prompt/response cycle with tool calling. Message with Web Search lets Claude reach the live web mid-message, which removes the need to pre-fetch context for time-sensitive workflows. Computer Use turns Claude into an agent that can drive a screen, click, type, scroll, screenshot, useful for automating any app that doesn't expose a clean API. The Skills surface (Create / Get / List / Delete Skill) lets you author reusable agent behaviours and call them from any workflow on your account. Count Tokens runs ahead of a call for cost-aware orchestration. Create Message Batch is the 50%-off async path for large jobs. Files upload and persist for cross-call reuse. The connection uses your own Anthropic API key, so usage and rate limits track to your account directly.

0triggers
21actions
≈ 2 minto set up
Freetier · no card
Actions

Do anything Anthropic can do, from a workflow.

Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.

ActionWhat it does
Analyze ImageSends an image to Claude for analysis (vision), via URL or base64 bytes alongside a text prompt. Use for OCR, chart extraction, accessibility alt-text, or visual QA flows.
Cancel Message BatchCancels a message batch that is still processing. Already-completed entries in the batch keep their results; in-flight ones get cancelled with no charge.
Computer UseSends a message with the computer-use tool, letting Claude take screenshots and click/type on a virtual desktop. Requires Opus 4.x or Sonnet 4.x; you provide the sandboxed desktop environment.
Count TokensCounts the number of tokens a Messages API call would consume without actually sending the message. Useful for cost estimation and to stay under context-window limits.
Create MessageSends a message to a Claude model and gets a response. The core Anthropic action; supports system prompts, multi-turn conversation, temperature, and stop sequences.
Create Message BatchCreates a batch of messages for async processing on the Messages API, with a 50% cost reduction and up to 24-hour turnaround. Perfect for bulk classification, summarization, or labeling jobs.
Create Message with ToolsSends a message with tool definitions. Claude returns tool_use blocks when it wants to call a function; you execute the call and feed results back as tool_result blocks for the next turn. The foundation for agentic workflows.
Create SkillCreates a new Claude Skill from a SKILL.md file. Skills are file-based; Claude reads the SKILL.md content directly. The action fetches your URL, uploads it as files[], and Anthropic returns a skill_id you can reference in subsequent Messages API calls.
Delete FileDeletes an uploaded file from Anthropic's file store. Use to clean up after a one-shot document analysis or to remove PII for compliance.
Delete SkillDeletes a custom Claude Skill by ID. The skill is removed from your workspace and can't be referenced in future Messages API calls.
Get FileReturns metadata about an uploaded file (filename, mime type, size, created_at). Use to verify an upload succeeded or to render a file picker.
Get Message BatchGets the status of a message batch: processing_status, request_counts, and (when complete) the results_url to download. Poll until status is "ended".
Get ModelReturns metadata about a specific Claude model (display name, context window, deprecation status). Useful for surfacing model availability in your UI.
Get SkillReturns details of a specific Claude Skill by ID. Useful to inspect what's currently registered before updating or deleting.
List FilesLists uploaded files in your Anthropic workspace with their IDs, names, and sizes. Used to render a file picker or for cleanup automations.
List Message BatchesLists all message batches and their processing status. Useful for batch-monitoring dashboards or for resuming work after a restart.
List ModelsLists available Claude models with their display names and context windows. Used to populate a dynamic model picker.
List SkillsLists all custom skills registered in your Anthropic workspace. Useful for skill-management dashboards.
Make API CallMakes a custom API call to any Anthropic endpoint with method, path, headers, and body. The escape hatch for newly-released APIs or fields that the typed actions don't yet expose.
Message with Web SearchSends a message with Anthropic's built-in web_search tool enabled. Claude fetches fresh web results inside the model call and cites them in the response. Removes the need to wire up an external search API.
Upload FileUploads a file (PDF, image, text) to Anthropic for use in messages via document blocks. Returns a file_id you reference instead of re-sending the bytes on every call.
Recipes

Pre-built Anthropic workflows.

Clone any recipe and customize it in one click. Every recipe is fully editable.

Before you build

Three things worth knowing.

Filter at the trigger

Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.

Authorize once, reuse anywhere

Connect Anthropic once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.

No JSON to read

Every Anthropic field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.

FAQ

Questions about the Anthropic integration.

If we missed yours, ping support. We usually reply within an hour.

How do I connect Anthropic to Tiny Command?
Open the Tiny Command workflow builder, drop in a Anthropic node, and click Connect. Authorize Anthropic once and any workflow on your account can use its triggers and actions. Most teams finish the connection in under two minutes.
What Anthropic triggers does Tiny Command support?
Tiny Command focuses on outbound actions for Anthropic today. Use Tiny Command's universal Webhook or Schedule trigger to start Anthropic workflows, then run any Anthropic action you need.
What Anthropic actions can I run from a workflow?
21 Anthropic actions are available out of the box, covering ai & ml operations like "Analyze Image". Every action accepts dynamic inputs from upstream nodes, whether that's a search result, an AI output, or a form field.
Is the Anthropic integration real-time?
Anthropic actions execute synchronously inside your workflow. Tiny Command waits for Anthropic's API to confirm before continuing to the next step, so downstream nodes can rely on the result.
Do I need to write code to use Anthropic with Tiny Command?
No. Every Anthropic trigger and action is fully configurable from the visual workflow builder. For edge cases that aren't covered, drop in a custom HTTP node and call any Anthropic API endpoint directly.
How much does the Anthropic integration cost?
There's a free tier you can start on without a credit card. Higher run volumes and team features come with paid plans. The Anthropic integration itself has no per-app surcharge.
Related

More ai & ml apps people connect.

Same category as Anthropic, ordered by how often teams pair them. Hover the carousel to pause.

Do more with Anthropic.

Wire it to Slack, Notion, HubSpot, Stripe, or any of the other 438 apps in our catalog. Setup takes roughly two minutes. Free to try, no credit card.