Doppler MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Doppler MCP Server get the API_KEY secret from production config"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Doppler MCP Server
A Model Context Protocol (MCP) server that wraps the Doppler CLI for seamless secrets management integration with Claude and other MCP clients.
Overview
This MCP server provides a bridge between MCP-compatible applications (like Claude Desktop) and the Doppler CLI, allowing you to manage secrets, projects, configs, and environments through natural language interactions.
Related MCP server: op-mcp
Prerequisites
Node.js 18 or higher
Doppler CLI installed and authenticated
An active Doppler account with appropriate permissions
Installation
From Source
# Clone or navigate to the repository
cd doppler-mcp-server
# Install dependencies
npm install
# Build the project
npm run buildConfiguration
Claude Desktop
Add this server to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"doppler": {
"command": "node",
"args": ["/absolute/path/to/doppler-mcp-server/build/index.js"]
}
}
}Other MCP Clients
For other MCP clients, configure them to run:
node /path/to/doppler-mcp-server/build/index.jsAvailable Tools
The server exposes the following Doppler CLI operations as MCP tools:
Secrets Management
doppler_secrets_get - Get a specific secret value
Parameters:
name(required),project,config
doppler_secrets_list - List all secrets in a config
Parameters:
project,config
doppler_secrets_set - Set a secret value
Parameters:
name(required),value(required),project,config
doppler_secrets_delete - Delete a secret
Parameters:
name(required),project,config
Project Management
doppler_projects_list - List all projects
Parameters: none
doppler_projects_create - Create a new project
Parameters:
name(required),description
Config Management
doppler_configs_list - List all configs in a project
Parameters:
project
doppler_configs_create - Create a new config
Parameters:
name(required),project(required),environment(required)
Environment Management
doppler_environments_list - List all environments in a project
Parameters:
project
Utility
doppler_run - Run a command with Doppler secrets injected
Parameters:
command(required),project,config
doppler_me - Get information about the authenticated user
Parameters: none
Usage Examples
Once configured, you can interact with Doppler through your MCP client:
"List all my Doppler projects"
"Get the API_KEY secret from my production config"
"Set DATABASE_URL to postgres://... in the dev config"
"Create a new project called my-app"
"Show me all secrets in the staging config"Authentication
This server uses the Doppler CLI's authentication. Make sure you've authenticated the Doppler CLI before using this server:
doppler loginYou can verify your authentication status:
doppler meDevelopment
Build
npm run buildWatch Mode
npm run watchHow It Works
This server:
Listens for MCP tool requests via stdio
Translates tool calls into Doppler CLI commands
Executes the commands using your local Doppler CLI installation
Returns the results in JSON format back to the MCP client
Troubleshooting
"Command not found: doppler"
Make sure the Doppler CLI is installed and available in your PATH:
which doppler
doppler --version"Authentication required"
Authenticate with Doppler:
doppler loginServer not appearing in Claude Desktop
Check that the path in
claude_desktop_config.jsonis correct and absoluteRestart Claude Desktop completely
Check the Claude Desktop logs for errors
Security Considerations
This server executes Doppler CLI commands with the permissions of the authenticated user
Secrets are transmitted through the MCP protocol - ensure your MCP client is trusted
The server does not store any secrets, it only proxies requests to the Doppler CLI
License
MIT
Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
Available Tools
11 toolsdoppler_configs_createC
Create a new config in a Doppler project
Inputs: name (required), project (required), environment (required).
doppler_configs_listC
List all configs in a Doppler project
Inputs: project.
doppler_environments_listC
List all environments in a Doppler project
Inputs: project.
doppler_meB
Get information about the current authenticated Doppler user
Inputs: no named parameters.
doppler_projects_createC
Create a new Doppler project
Inputs: name (required), description.
doppler_projects_listA
List all Doppler projects
Inputs: no named parameters.
doppler_runB
Run a command with Doppler secrets injected as environment variables
Inputs: command (required), project, config.
doppler_secrets_deleteC
Delete a secret from Doppler
Inputs: name (required), project, config.
doppler_secrets_getC
Get a secret value from Doppler
Inputs: name (required), project, config.
doppler_secrets_listC
List all secrets in a Doppler config
Inputs: project, config.
doppler_secrets_setC
Set a secret value in Doppler
Inputs: name (required), value (required), project, config.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose targeting specific resources and actions, with no ambiguity between them. For example, doppler_secrets_get retrieves a single secret value, while doppler_secrets_list enumerates all secrets, and doppler_run is uniquely for executing commands with injected secrets.
All tools follow a consistent doppler_<resource>_<action> naming pattern using snake_case throughout. This predictable structure makes it easy to understand each tool's function at a glance, such as doppler_configs_create and doppler_secrets_delete.
With 11 tools, the server is well-scoped for managing Doppler projects, configs, environments, and secrets. Each tool earns its place by covering essential CRUD operations and specific workflows like doppler_run, avoiding both bloat and gaps.
The toolset provides strong coverage for core Doppler operations, including project, config, environment, and secret management with create/list/get/set/delete actions. A minor gap exists in missing update operations for configs or projects, but agents can work around this by recreating resources as needed.
Maintenance
Related MCP Connectors
Secrets for developers and agents—secure context and workflows without exposing secret values.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Encrypted secret store and rotation for autonomous agent credentials
Your Supabase account in natural language: run SQL, apply migrations, manage tables, storage, edge f
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to interact with the Doppler API for secrets management, including listing, retrieving, and updating secrets across projects and configs. Supports both read-only and full access modes with token-based authentication.3,815 npm8Apache 2.0- FlicenseNot gradedqualityDmaintenanceEnables to manage 1Password resources including vaults, items, documents, users, groups, and more through the 1Password CLI, exposing 65 tools for comprehensive password management via natural language.-
- AlicenseAqualityDmaintenanceEnables managing DigitalOcean cloud resources, including Droplets, databases, domains, and more, via natural language.121MIT
- AlicenseBqualityDmaintenanceEnables natural language management of Doppler secrets, projects, configs, and environments by wrapping the Doppler CLI for use with MCP clients like Claude Desktop.11MIT