How to Use the eSputnik MCP in Pydantic AI

Q: How do I register the eSputnik MCP server in Pydantic AI?

Install pydantic-ai-slimmcp and use MCPToolset with your server URL. Pass this toolset to your Agent to expose tools like sendsmartsend with automatic runtime validation.

Q: What happens if the eSputnik MCP Server returns unexpected data to Pydantic AI?

If tools like getaccountinfo return unexpected fields, Pydantic AI raises a validation error. This prevents your agent from acting on corrupted or misaligned API responses.

Q: Can I safely manage contact groups in eSputnik using Pydantic AI?

Yes, you can use listgroups and detachfromgroup to manage segments. The framework ensures group IDs and contact identifiers are typed strictly as strings or integers before execution.

Q: How does the agent handle unsubscribed contacts?

The agent calls listunsubscribed to fetch the list of opted-out emails. It then cross-references this data with your database to keep your local records synchronized.

Q: How is the privacy of unsubscribed email lists handled during MCP execution?

Data fetched via listunsubscribed is processed entirely in memory within an ephemeral, zero-trust V8 sandbox. Authentication is handled at the proxy level, keeping your API tokens isolated from the client.

Drive type-safe eSputnik marketing campaigns with strict runtime validation using Pydantic AI and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eSputnik MCP to Pydantic AI

Create your Vinkius account to connect eSputnik 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 eSputnik with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe contact creation

The `create_contact` tool registers new subscribers while Pydantic AI guarantees the payload matches your strict data models. If the email format is invalid or a phone number is missing digits, the agent fails immediately. This strict validation prevents bad data from corrupting your lists. You avoid API errors on `attach_to_group` because the agent cannot pass malformed contact objects to the server.

Structured search and retrieval via MCP Server

The `search_contacts` tool finds specific users by email or phone, returning structured data that Pydantic AI validates at runtime. The framework parses the response into typed Python objects, eliminating silent failures. If the API return schema changes, your agent raises a validation error instead of hallucinating missing fields. This makes tools like `get_contact` safe for production workflows where accuracy is critical.

Validated event triggering

The `trigger_event` tool generates system events to launch automated marketing campaigns. Your Pydantic AI agent validates the event payload structure before sending the request. You can verify message delivery status with `get_message_status` knowing the returned status string matches your internal Enum. No unexpected null values will break your downstream application logic.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use `MCPToolset` with your server URL. Pass this toolset to your `Agent` to expose tools like `send_smart_send` with automatic runtime validation.

If tools like `get_account_info` return unexpected fields, Pydantic AI raises a validation error. This prevents your agent from acting on corrupted or misaligned API responses.

Yes, you can use `list_groups` and `detach_from_group` to manage segments. The framework ensures group IDs and contact identifiers are typed strictly as strings or integers before execution.

The agent calls `list_unsubscribed` to fetch the list of opted-out emails. It then cross-references this data with your database to keep your local records synchronized.

Data fetched via `list_unsubscribed` is processed entirely in memory within an ephemeral, zero-trust V8 sandbox. Authentication is handled at the proxy level, keeping your API tokens isolated from the client.

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