How to Use the DeepSeek MCP in Claude Code

Q: How do I add the DeepSeek MCP Server to Claude Code?

Run the command claude mcp add --transport http deepseek -- in your terminal. Make sure all flags come before the server name, and verify the connection by running claude mcp list.

Q: Can I run DeepSeek reasoning tasks headlessly with Claude Code?

Yes, Claude Code calls the deepreasoning tool to process complex problems from the command line. You can pipe the terminal output directly into files or other scripts for automated workflows.

Q: How does Claude Code monitor my DeepSeek token consumption?

The CLI agent queries the gettokenusage tool to print exact token metrics to your terminal screen. This lets you track the resource cost of your automated scripts in real time.

Q: Can I list my active models using the command line?

Yes, you can ask the CLI agent to run the listmodels tool to see every model available on your account. It will output the list directly to stdout so you can filter it with grep.

Run DeepSeek reasoning and model management directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepSeek MCP to Claude Code

Create your Vinkius account to connect DeepSeek 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 DeepSeek with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Command-Line Model and Token Auditing

The `get_token_usage` tool allows Claude Code to fetch precise usage metrics directly to your terminal. When running automated shell scripts or CI/CD pipelines, you can pipe this MCP output directly into your monitoring logs. By calling `get_balance` and `get_billing_details`, your CLI agent can block expensive script runs if your account balance drops below a threshold. This keeps your automated terminal tasks from running up surprise bills when you're not looking.

Headless Deep Reasoning for Terminal Scripts

The `deep_reasoning` tool injects DeepSeek's advanced logical planning directly into your headless shell sessions. SREs can use this to analyze system logs and generate complex bash scripts based on the model's internal thinking steps. Because Claude Code operates entirely in the terminal, it uses `chat_completion` to output raw text that you can pipe straight into other command-line utilities. No browser or heavy GUI required.

Dynamic Token and Model Management for Claude Code

The `list_api_tokens` tool gives Claude Code the power to manage your API keys directly from your terminal prompt. You can check active credentials without opening a browser or logging into the DeepSeek console. This MCP Server also exposes `list_models` and `get_model_details`, letting your CLI agent query metadata and switch target endpoints dynamically during automated test runs.

Setup guide

Set up DeepSeek 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 deepseek-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http deepseek-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 DeepSeek 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": {
    "deepseek-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 DeepSeek. 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 DeepSeek 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 DeepSeek MCP in Claude Code

Run the command `claude mcp add --transport http deepseek -- ` in your terminal. Make sure all flags come before the server name, and verify the connection by running `claude mcp list`.

Yes, Claude Code calls the `deep_reasoning` tool to process complex problems from the command line. You can pipe the terminal output directly into files or other scripts for automated workflows.

The CLI agent queries the `get_token_usage` tool to print exact token metrics to your terminal screen. This lets you track the resource cost of your automated scripts in real time.

Yes, you can ask the CLI agent to run the `list_models` tool to see every model available on your account. It will output the list directly to stdout so you can filter it with grep.

Vinkius routes all requests through an ephemeral V8 sandbox that decrypts your credentials only during execution. When Claude Code calls `list_api_tokens`, the keys are processed securely and never 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