How to Use the MPU-Manager MCP in Claude Code

Q: What's the command to connect Claude Code to MPU-Manager?

The command is claude mcp add --transport http mpu-manager-mcp -- . After that, you can verify the connection is working by running claude mcp list.

Pipe MPU-Manager production data into your shell scripts and CI/CD jobs with Claude Code. Headless, terminal-native, and built for automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect MPU-Manager MCP to Claude Code

Create your Vinkius account to connect MPU-Manager to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup MPU-Manager with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Production Status Checks

Integrate MPU-Manager directly into your deployment pipelines. Start your CI job with a call to `check_mpumanager_status` to make sure the API is online. If it's not, the build fails fast, saving you time. You can then pipe the output from `list_cases` into a tool like `jq` to count open, high-priority cases. This lets you automatically block a release if there are critical issues pending in the production system.

Manage Crew and Cases from the Terminal

You don't need a UI to manage your production schedule. A few simple shell commands are all it takes to interact with the MPU-Manager MCP server. It’s perfect for engineers who live on the command line. Check your schedule with `claude mcp call mpu-manager-mcp list_appointments`. Create a new incident report with `create_case`. You can build simple bash aliases to make these daily tasks even faster.

Export Production Data for Analysis

Set up a cron job to pull your production data automatically. Have it call `list_reports` and `list_cases` every night, piping the raw JSON output straight into a file. From there, your script can upload the data to a storage bucket or a data warehouse. It's a straightforward way to build an automated data pipeline for your production metrics without needing a complex ETL tool.

Setup guide

Set up MPU-Manager 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 mpu-manager-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http mpu-manager-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 MPU-Manager 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": {
    "mpu-manager-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 MPU-Manager. 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 MPU-Manager 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 MPU-Manager MCP in Claude Code

First, add your Vinkius token as a secret in your CI provider. Then, in your pipeline script, run `claude mcp add` to configure the MPU-Manager server. Now you can make calls like `claude mcp call mpu-manager-mcp list_cases` and use the output in your job.

The command is `claude mcp add --transport http mpu-manager-mcp -- `. After that, you can verify the connection is working by running `claude mcp list`.

Absolutely. The output is JSON, so you can pipe it directly to command-line tools like `jq` for filtering and transformation. This is ideal for extracting specific fields, like a case ID or an appointment time, inside a shell script.

Yes. As long as the container has the Claude Code binary and can reach your Vinkius MCP endpoint, it works just like it does on your local machine. It's a common way to run scheduled tasks against MPU-Manager.

When you use Claude Code, it transmits your case and appointment data over a secure channel to the server. The MPU-Manager server itself is ephemeral; Vinkius ensures no data is written to disk. Your information is only processed in memory for that single API call.

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