How to Use the Dashly MCP in Pydantic AI

Q: What happens if the Dashly API returns an unexpected field to my Pydantic AI agent?

Your code will raise a ValidationError. This fail-loudly approach is a core feature, preventing your agent from processing incomplete or malformed data from Dashly without your knowledge.

Q: Is this different from using the old MCPServerHTTP class?

Yes, using MCPToolset is the modern, unified approach in Pydantic AI. It's simpler and works consistently across different server types, whereas MCPServerHTTP is now deprecated.

Get type-safe, validated access to your Dashly data in Python with Pydantic AI. No more silent failures or bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dashly MCP to Pydantic AI

Create your Vinkius account to connect Dashly 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 Dashly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Interact with Dashly, Safely

When your agent calls `get_user_details` or `list_conversations`, Pydantic AI validates the response from this MCP server against a Pydantic model. If the API ever returns something unexpected, your code raises a `ValidationError` immediately. This means no more silent data corruption or guessing games. You know the data you're working with is exactly what you expect, every single time. It's about building reliable systems that don't fail quietly.

Use Any LLM for Customer Support

Pydantic AI doesn't lock you into one model provider. You can use the Dashly tools—like `send_reply` and `track_event`—with an agent powered by OpenAI, Anthropic, Gemini, or even a local model you run yourself. The framework handles the tool-calling logic. You just focus on the task, knowing the underlying data operations are strictly validated, no matter which LLM is driving the agent.

Add the Dashly MCP Server with One Line

Integration is dead simple. You instantiate the `MCPToolset` with the server URL and pass it to your agent. All the Dashly tools, from `list_channels` to `set_user_props`, become available instantly. Pydantic AI handles all the HTTP requests and response parsing for you. You just call the functions as if they were native Python methods, and you get validated Pydantic objects back.

Setup guide

Set up Dashly 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": {
        "dashly-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Dashly 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 Dashly. 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 Dashly 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 Dashly MCP in Pydantic AI

It validates every response from the Dashly MCP server against a Pydantic model at runtime. If a field is missing, has the wrong type, or is unexpected, Pydantic AI will raise an error instead of letting your agent use bad data.

Yes. Pydantic AI is model-agnostic. As long as your local LLM supports tool-calling, you can connect it to the Dashly tools through this server.

Your code will raise a `ValidationError`. This fail-loudly approach is a core feature, preventing your agent from processing incomplete or malformed data from Dashly without your knowledge.

Yes, using `MCPToolset` is the modern, unified approach in Pydantic AI. It's simpler and works consistently across different server types, whereas `MCPServerHTTP` is now deprecated.

Every connection is handled by a dedicated, isolated server instance that exists only for the duration of your requests. Your sensitive conversation data is processed in an ephemeral environment and is never co-mingled or persisted on our end.

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