The Anthropic MCP for putting Claude inside your workflows
Connect your Anthropic API key once and Claude becomes a building block: single messages for live steps, batches at reduced cost for bulk work, and retrieval to collect the results.
What the Anthropic MCP connector does
The Anthropic connector for Mattering Automations wires Claude into the canvas with three nodes: Claude Message generates a response inside a workflow step, Claude Batch submits a list of message requests for asynchronous processing, and Claude Get Batch polls a batch and returns its parsed results.
Every node speaks MCP, the open protocol for connecting AI assistants to tools, so Claude, ChatGPT, and any MCP-capable assistant can use them, alongside Matter, the AI assistant built into the platform. That composes in interesting ways: an assistant can orchestrate a workflow that itself calls Claude for the heavy generation steps.
Batching is the quiet workhorse. Anthropic's Message Batches API processes requests asynchronously at half the standard token price per Anthropic's pricing documentation, which is the right shape for the bulk work automations tend to do: summarize every open ticket, draft fifty outlines, classify a backlog.
One connection, three surfaces
- Visual automations. Drag Anthropic nodes onto the canvas and wire them to triggers, conditions, and other apps.
- AI agents, yours or ours. These nodes speak MCP, the open protocol, so Claude, ChatGPT, and any MCP-capable assistant can use them, and Matter, the agent built into the platform, uses them natively.
- The whole platform. Combine with native tasks, projects, and other connectors, no middleware in between.
Every Anthropic node, ready to drop on the canvas
3 nodes, generated from the connector itself so this list always matches what ships. Expand a category to browse.
Read and query nodes 1
Claude Get Batch
Fetch the status and results of a Claude message batch
Action nodes 2
Claude Batch
Submit a batch of message requests to Claude for asynchronous processing at half the standard token cost
Claude Message
Generate a message with Claude
Connecting Anthropic takes one credential
Create an API key in the Anthropic Console at console.anthropic.com under Settings, then API keys. Keys start with sk-ant.
In the Anthropic Console, create an API key.
In Mattering Automations, open Connectors, choose Anthropic, and create a credential with the key.
The connector verifies the key against Anthropic's models endpoint.
The Claude nodes appear in the canvas palette, ready to use.
Common uses for the Anthropic MCP
Summaries inside any workflow
Drop Claude Message between a data-gathering node and a delivery node: meeting notes condensed, tickets summarized, reports turned into two-paragraph digests.
Bulk generation overnight at reduced cost
Queue hundreds of drafts, classifications, or rewrites as one batch in the evening and collect the results with Get Batch in the morning, at half the per-token price of live calls.
Classification and routing
Let Claude read an inbound item (a form submission, a support thread, a lead) and return a category the workflow branches on.
Agent-orchestrated generation
An MCP-connected assistant designs the workflow and delegates the generation steps to Claude nodes, so orchestration and heavy lifting use the right model for each job.
Content pipelines
Chain keyword research from another connector into Claude Message for outlines, then into your review queue in Mattering Productivity, keeping a human on publish.
Example: Fifty article outlines, batched overnight
Built on the Automations canvas in a few minutes, or described in plain language to Matter and built for you.
Trigger: a scheduled run fires after the workday ends.
A query node reads this week's approved topics from a Mattering database.
Anthropic: Claude Batch submits one outline request per topic in a single batch.
Next morning, Anthropic: Claude Get Batch collects the finished outlines and a task per outline is created for editorial review.
Anthropic MCP questions, answered
Can an AI agent call Claude through this MCP?
Yes. Matter and any MCP-connected assistant, including Claude and ChatGPT, can run the Claude Message node for live generation and manage batches through Claude Batch and Claude Get Batch, the same nodes available on the automation canvas.
Does this work with Claude, ChatGPT, or other AI assistants?
Yes. Mattering exposes these nodes over MCP, an open protocol for connecting AI assistants to tools, so any MCP-capable assistant can connect to your workspace and use them. Matter, the assistant built into the platform, uses the same nodes natively.
Which Claude models can the nodes use?
Any model your Anthropic API key can access; the model id is a per-node setting. The node default tracks a current general-purpose Claude model, and you can pin a specific model id per workflow step.
How does batching save money?
Anthropic's Message Batches API processes requests asynchronously, typically within an hour and at half the standard per-token price per Anthropic's pricing documentation. The Claude Batch node submits the batch and Claude Get Batch retrieves parsed per-request results once processing ends.
What credential does the connector use?
An Anthropic API key from the Anthropic Console, sent as the x-api-key header and stored encrypted in Google Secret Manager. Keys can be rotated in the Console and updated on the connector at any time.
What are the API rate limits?
Anthropic enforces per-organization rate limits that vary by usage tier; Anthropic's documentation is the source of truth for current numbers. Batches sidestep most throughput concerns because Anthropic schedules the processing.
What is not supported?
The connector covers the Messages and Message Batches APIs. Streaming responses, file uploads, and the Anthropic Console's administrative APIs are not exposed as nodes.
Put Anthropic to work inside your workspace
Connect once, then use every node in visual automations and AI agent workflows across the Mattering platform.
All product names, logos, and brands are property of their respective owners and are used for identification purposes only. Use of these names, logos, and brands does not imply endorsement or affiliation. Anthropic is a product of its respective owner; Mattering is an independent platform.