How to Use the Automate.io MCP in Claude Code

Q: How do I add the Automate.io MCP Server to Claude Code?

Run claude mcp add --transport http automateio -- in your terminal. This adds the MCP Server configuration to your local /.claude.json file.

Q: Can I pipe Automate.io run logs to other CLI tools using Claude Code?

Yes, you can ask Claude Code to output the results of listbotruns as raw JSON. You can then pipe that data directly into tools like jq or local log files.

Q: How do I check my monthly API usage?

Simply ask Claude Code to check your usage. It will run getusage and print your current execution count and billing tier limits directly in your terminal.

Q: Is my Automate.io usage data secure with Claude Code?

Yes, all calls to getusage and bot configurations run through an ephemeral V8 sandbox. Vinkius handles authentication securely, ensuring no credentials or raw metrics are stored on disk.

Manage your Automate.io workflows from your terminal with Claude Code headless execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Automate.io MCP to Claude Code

Create your Vinkius account to connect Automate.io to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Automate.io with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query workflow execution runs via Claude Code CLI

Executing the `list_bot_runs` tool retrieves chronological execution histories directly into your terminal session. Claude Code uses this MCP Server to pipe this data into shell scripts or local logs, allowing you to debug broken webhooks without opening a browser. When a cron job fails, you ask Claude Code to check the status of your Automate.io workflows. It runs `get_bot` to inspect the configuration, identifies the failing node, and outputs the exact payload error directly to your standard output.

Audit workspace integrations using this MCP Server

Querying the `list_connections` tool lists every authenticated application connection in your Automate.io workspace. Claude Code uses this to verify credential status before running deployment scripts that depend on external APIs. If a deployment requires a new service, Claude Code calls `list_apps` to verify compatibility. This outputs the required configuration flags so your CI/CD pipeline can run without manual intervention.

Monitor account usage limits in your terminal

Fetching data with the `get_usage` tool pulls active billing and execution metrics from your Automate.io account. Claude Code checks these limits during automated testing runs, letting you script alerts if usage exceeds safety thresholds. By pairing this with `list_bots`, Claude Code generates terminal-friendly reports of your active workflows. You can pipe this output directly into local monitoring tools or slack alerts.

Setup guide

Set up Automate.io MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see automateio-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Automate.io transactions." It will automatically discover and invoke the available Automate.io tools.

Terminal

claude mcp add --transport http automateio-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Automate.io MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "automateio-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Automate.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Automate.io now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Automate.io MCP in Claude Code

Run `claude mcp add --transport http automateio -- ` in your terminal. This adds the MCP Server configuration to your local `~/.claude.json` file.

Yes, you can ask Claude Code to output the results of `list_bot_runs` as raw JSON. You can then pipe that data directly into tools like `jq` or local log files.

This server focuses on auditing and monitoring. Claude Code can check bot states using `list_bots` and `get_bot`, but you must use the web UI to modify active statuses.

Simply ask Claude Code to check your usage. It will run `get_usage` and print your current execution count and billing tier limits directly in your terminal.

Yes, all calls to `get_usage` and bot configurations run through an ephemeral V8 sandbox. Vinkius handles authentication securely, ensuring no credentials or raw metrics are stored on disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript