How to Use the Doppler MCP in Pydantic AI

Q: Can Pydantic AI agents list Doppler workspaces?

Absolutely. Use listworkspaces as a tool to discover your available Doppler units. Pydantic AI will validate the result list automatically.

Q: How do I prevent Pydantic AI from deleting the wrong Doppler secrets?

The deletesecrets tool requires an explicit list of secret names. Your Pydantic AI agent's schema validation ensures you don't pass an empty or incorrect array.

Strictly typed secret management for Pydantic AI agents using the Doppler MCP server.

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 Pydantic AI

Create your Vinkius account to connect Doppler to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe secret retrieval for Pydantic AI

Every call to `get_secret` returns data that your Pydantic AI agent can immediately validate against your models. This stops bad data from entering your logic. If the API returns a malformed structure, the agent throws a validation error. You get immediate feedback rather than silent failures.

Validate Doppler projects in Pydantic AI

Use `list_projects` to pull your workspace map. Your agent validates these names against your expected Pydantic schemas before proceeding. This ensures your agent only operates within authorized projects. It adds a layer of safety before you call `list_configs`.

Audit trail logging for Pydantic AI

Integrate `list_activity_logs` into your agent's post-execution checks. Your Pydantic AI agent confirms that its changes were recorded correctly in Doppler. It verifies the timestamp and the specific config affected. This is essential for maintaining a clear record of your automation behavior.

Setup guide

Set up Doppler MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "doppler-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Doppler tools.",
)

result = await agent.run("List recent Doppler transactions")
print(result.output)

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 Pydantic AI

Define a Pydantic model for your secret structure. When the MCP server returns data from `get_secret`, your agent validates the output against that model.

Absolutely. Use `list_workspaces` as a tool to discover your available Doppler units. Pydantic AI will validate the result list automatically.

The MCP server uses standard encryption for transit. Your Pydantic AI agent only receives the specific value requested through a secure, validated tool call.

The `delete_secrets` tool requires an explicit list of secret names. Your Pydantic AI agent's schema validation ensures you don't pass an empty or incorrect array.

Audit logs are stored on the Doppler side. Your Pydantic AI agent simply queries `list_activity_logs` to verify that your security policies are being followed.

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