How do I create a Doppler Service Token?

Log in to the [**Doppler Dashboard**](https://dashboard.doppler.com), select your project, go to **Settings** > **Tokens** and click **Generate Token**. Choose the scope (project + config/environment), set the access level (Read or Read+Write) and copy the token immediately — it won't be shown again.

Can I update multiple secrets at once?

Yes! Use the `change_secrets` tool with a JSON object mapping names to values, e.g. `{"DATABASE_URL":"postgres://new-host","API_KEY":"sk-new"}`. This creates or updates all specified secrets in a single atomic operation.

What is the difference between a Personal Token and a Service Token?

A **Personal Token** is scoped to your user account and can access all workspaces and projects you have permission for. A **Service Token** is scoped to a specific project and config, with either read-only or read+write access. Service tokens are recommended for CI/CD and automated integrations, while personal tokens are better for development and admin tasks.

Can I view the activity history for a project?

Yes! Use the `list_activity_logs` tool with the project_slug to see all audit events (secret reads, writes, config changes, user additions). Optionally filter by config_name to see activity for a specific environment only. Each log entry shows who performed the action, when, and what was affected.

Doppler MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Doppler
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Doppler through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Doppler "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Doppler?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Doppler MCP Server

Connect your Doppler account to any AI agent and take full control of your secrets management through natural conversation.

Pydantic AI validates every Doppler tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Workspace & Project Discovery — List all workspaces and projects with their names, slugs and descriptions
Config (Environment) Management — View all configs (development, staging, production) per project and their metadata
Secret Auditing — List all secret names and computed values for any config, with environment fallback resolution
Secret Operations — Add, update and delete secrets in any environment with atomic change requests
Activity Logging — Review the full audit log of secret reads, writes, config changes and user activity per project

The Doppler MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Doppler to Pydantic AI via MCP

Follow these steps to integrate the Doppler MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Doppler with type-safe schemas

Why Use Pydantic AI with the Doppler MCP Server

Pydantic AI provides unique advantages when paired with Doppler through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Doppler integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Doppler connection logic from agent behavior for testable, maintainable code

Doppler + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Doppler MCP Server delivers measurable value.

Type-safe data pipelines: query Doppler with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Doppler tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Doppler and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Doppler responses and write comprehensive agent tests

Doppler MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Doppler to Pydantic AI via MCP:

change_secrets

Provide project_slug, config_name and a JSON object mapping secret names to values. For example: {"DATABASE_URL":"postgres://...","API_KEY":"sk-..."}. Existing secrets not included are not modified. Add or update secrets in a Doppler config

delete_secrets

Provide project_slug, config_name and comma-separated secret names. WARNING: deleted secrets cannot be recovered. If a secret inherits a value from a parent, it reverts to that value. Delete secrets from a Doppler config

get_account

Returns account email, name, and token metadata (type, scope, permissions). Use this to verify your token is working correctly and understand its access level. Get the current Doppler account details

get_config

Returns config name, project, root status, associated environment template, creation date and locked status. Get details for a specific Doppler config

get_project

Provide the project slug (e.g. "my-api-project") and optionally the workspace slug. Get details for a specific Doppler project

get_secret

Returns the secret name and its resolved value with fallbacks from parent environments applied. Get a specific secret value from a Doppler config

list_activity_logs

Each entry shows who performed what action, when and the affected config. Optionally filter by config_name. Useful for security auditing and compliance. List activity logs for a Doppler project

list_configs

Each config represents a deployment environment (development, staging, production) and contains its own set of secrets. Returns config name, project slug, root status and environment template used. List configs (environments) for a Doppler project

list_environments

g. development, staging, production, preview). Returns environment name, slug and whether it is the default environment. List Doppler environment types

list_projects

Optionally filter by workspace slug. Each project contains configs (environments) and secrets. Returns project name, slug, description, and creation date. List Doppler projects

list_secrets

Returns each secret's name, computed value (with environment fallbacks applied), visibility status. Provide the project_slug and config_name. List all secrets for a Doppler config

list_workspaces

A workspace is the top-level organizational unit in Doppler that groups projects. Returns workspace name, slug and creation date. List all Doppler workspaces

Example Prompts for Doppler in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Doppler immediately.

"Show me all configs for my 'backend-api' project."

"Update the DATABASE_URL secret in my prod config to point to the new database."

"Who changed secrets in my project in the last week?"

Troubleshooting Doppler MCP Server with Pydantic AI

Common issues when connecting Doppler to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Doppler + Pydantic AI FAQ

Common questions about integrating Doppler MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Doppler MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.