How to Use the Anthropic MCP in Claude Code

Q: Can Claude Code help me monitor my Anthropic API spending?

Yes, the CLI agent can run estimatecost against local files before sending them. This lets you budget your automated shell scripts and CI pipeline runs before spending any money.

Q: How does Claude Code fetch the latest Anthropic model specs?

The tool uses getmodelspecs through the MCP Server to pull details like context window limits directly into your terminal. This helps you write bash scripts that dynamically adjust input sizes based on the target model.

Q: Can I stop a batch job directly from a shell script?

Yes, you can run cancelbatch with the batch ID from your terminal. This immediately stops the remote job and prevents further charges.

Pipe terminal outputs directly into cheap Anthropic batch runs and track your API quotas right from your shell.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anthropic MCP to Claude Code

Create your Vinkius account to connect Anthropic 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 Anthropic with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless batch processing for terminal pipelines

This MCP Server allows your CLI agent to trigger `create_batch` and `get_batch_results` inside your bash scripts or CI/CD pipelines. You can pipe a list of log files or code files directly into a batch job for offline analysis. This is perfect for nightly security audits or automated documentation updates. Your terminal agent handles the async polling and outputs the final JSON directly to your stdout.

Shell-integrated rate limit and quota monitoring

The terminal agent uses `check_rate_limits` to monitor your API usage directly from the command line. SREs and DevOps engineers can run this check before launching massive automated code-generation scripts. It prints your remaining requests and tokens directly to the terminal. You can easily integrate this check into your pre-commit hooks or deployment scripts to avoid API failures mid-run.

Instant command-line cost estimation

This MCP Server exposes `estimate_cost` so you can quickly calculate the cost of piping massive files to Claude. Before running a terminal command that feeds a 10,000-line log file to the model, you get an exact price estimate. This prevents surprise bills during automated terminal runs. You can script a fallback to a smaller model if the estimated cost exceeds your threshold.

Setup guide

Set up Anthropic 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 anthropic-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http anthropic-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 Anthropic 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": {
    "anthropic-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 Anthropic. 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 Anthropic 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 Anthropic MCP in Claude Code

You can pass a list of files to the terminal agent and have it run `create_batch`. The agent returns a batch ID, allowing you to run other terminal commands while the API processes your data.

Yes, the CLI agent can run `estimate_cost` against local files before sending them. This lets you budget your automated shell scripts and CI pipeline runs before spending any money.

The tool uses `get_model_specs` through the MCP Server to pull details like context window limits directly into your terminal. This helps you write bash scripts that dynamically adjust input sizes based on the target model.

Yes, you can run `cancel_batch` with the batch ID from your terminal. This immediately stops the remote job and prevents further charges.

Vinkius executes the server in an isolated V8 sandbox. Your credentials and terminal inputs are sent directly to the API, meaning no intermediate logs or files are stored.

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