How to Use the Doppler MCP in Claude Code

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

Run the command claude mcp add --transport http doppler -- in your terminal. This configures the connection in your local /.claude.json file so the CLI agent can access your secrets.

Q: Can I use Claude Code to audit Doppler access?

Yes, you can run listactivitylogs through the CLI to output audit trails directly to your terminal. This helps DevOps engineers quickly verify who modified a configuration during an incident response.

Q: What happens if a Doppler workspace has hundreds of secrets?

The MCP agent uses listsecrets to retrieve the entire list, which might consume significant token context. You can instruct the agent to query specific keys using getsecret instead to keep terminal output clean.

Pipe Doppler secrets directly into your terminal pipelines and shell scripts 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 Doppler MCP to Claude Code

Create your Vinkius account to connect Doppler 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 Doppler with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch Doppler secrets directly in Claude Code

`get_secret` retrieves individual values from your Doppler configs and prints them directly to your terminal. Claude Code uses this to populate environment variables for local testing scripts. You can pipe these outputs directly into other CLI utilities. This removes the need to store unencrypted env files on your local hard drive.

Navigate Doppler workspaces from the CLI

`list_workspaces` allows Claude Code to discover and switch between your organizational units. The terminal agent lists your projects across different workspaces without requiring browser access. Once selected, the agent calls `list_configs` to show you active deployment environments. You can inspect your target configurations directly within your active terminal session.

Update Doppler secrets via this MCP Server

`change_secrets` enables Claude Code to write multiple environment variables to a specific config at once. The CLI agent accepts a JSON payload and updates your Doppler target instantly. This is ideal for automated CI/CD setups or quick terminal-based rotations. You supply the parameters, and the agent executes the update without manual web console navigation.

Setup guide

Set up Doppler 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 doppler-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http doppler-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 Doppler 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": {
    "doppler-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 Doppler. 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 Doppler 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 Doppler MCP in Claude Code

Run the command `claude mcp add --transport http doppler -- ` in your terminal. This configures the connection in your local `~/.claude.json` file so the CLI agent can access your secrets.

Yes, you can run `list_activity_logs` through the CLI to output audit trails directly to your terminal. This helps DevOps engineers quickly verify who modified a configuration during an incident response.

The terminal client uses your single Vinkius endpoint token to authorize all requests. Vinkius manages the underlying Doppler API authentication, so you do not need to expose your master tokens to the CLI.

The MCP agent uses `list_secrets` to retrieve the entire list, which might consume significant token context. You can instruct the agent to query specific keys using `get_secret` instead to keep terminal output clean.

Your raw secret values are processed inside secure, ephemeral V8 isolates on Vinkius. We never write your secrets or workspace metadata to disk, ensuring your runtime credentials remain strictly in-memory.

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