How to Use the Ada MCP in Pydantic AI

Q: How does this server protect my Ada customer profiles?

All customer profiles retrieved via getenduser are validated in your local memory space. Vinkius runs the underlying MCP Server in a zero-trust V8 isolate sandbox, ensuring support metadata is never cached or exposed to third parties.

Force your Ada support data through strict runtime validation using the Pydantic AI framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ada MCP to Pydantic AI

Create your Vinkius account to connect Ada 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 Ada with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Ada Article Creation in Pydantic AI

Never let your agent publish broken or malformed help articles to your customers. When creating content via `create_article`, Pydantic AI validates the title and body against strict Python schemas before sending the payload via MCP to Ada. If your agent tries to inject invalid HTML or missing fields, the framework raises a validation error immediately. This loud failure prevents corrupted data from ever reaching your live support database.

Validate End-User Profiles at Runtime

Clean up your customer metadata before your agent processes it. By calling `get_end_user`, the agent pulls custom support variables and parses them directly into Pydantic models, forcing strict type compliance on every user field. This setup eliminates silent failures caused by unexpected null values or modified API schemas. Your agent either gets the exact customer profile structure it expects, or it halts execution so you can fix the schema drift.

Audit Chats Securely with Pydantic AI MCP Server

Ensure your conversation logs match your internal database schemas. The agent uses `list_conversations` to ingest active and past customer chats, immediately parsing the timestamps, user IDs, and transcriptions into typed Python objects. This strict validation makes it safe to feed raw support data into downstream pipelines. You can also audit your support catalog by running `list_articles` to verify that every live help document contains required metadata fields.

Setup guide

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

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

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

The framework will raise a ValidationError at runtime. This prevents your agent from working with corrupted support data or hallucinating fields that don't actually exist in your Ada environment.

You initialize the MCPToolset using the Vinkius HTTP endpoint. Pass this toolset directly to your Agent instance, and the framework auto-discovers tools like `list_conversations` and `create_article`.

Yes, you can define a Pydantic model for your articles, and the agent will validate the output of `list_articles` against this model, ensuring all your help docs meet your formatting standards.

Yes, Pydantic AI handles the validation layer independently of the LLM. You can use OpenAI, Anthropic, or local models to manage your Ada support workflows while maintaining the same MCP safety guarantees.

All customer profiles retrieved via `get_end_user` are validated in your local memory space. Vinkius runs the underlying MCP Server in a zero-trust V8 isolate sandbox, ensuring support metadata is never cached or exposed to third parties.

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