How to Use the Aidbase MCP in Pydantic AI

Plug your Pydantic AI agents into this Aidbase MCP Server for type-safe customer support automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aidbase MCP to Pydantic AI

Create your Vinkius account to connect Aidbase 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 Aidbase with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate this Aidbase MCP Server inbox status with Pydantic AI

`list_aidbase_inbox_knowledge` fetches the exact documents backing your email support automation. Your Pydantic AI agent validates this response against strict Python type schemas, ensuring no malformed URLs or empty text blocks corrupt your application state. If the Aidbase API returns an unexpected null value, your Pydantic AI code raises an immediate validation error instead of failing silently downstream. This strictness keeps your production support pipelines clean and predictable.

Audit support widget configurations safely

`list_aidbase_chatbots` retrieves metadata for all active customer-facing widgets on your site. Pydantic AI parses this list into structured models, letting you verify that every active bot has a valid fallback email and correct language settings. This Pydantic AI runtime validation guarantees that your application logic never operates on corrupted Aidbase configurations. You catch setup errors during development before they affect your live web visitors.

Retrieve specific email inbox configurations

`get_aidbase_inbox` pulls the detailed schema and routing rules for a designated support email channel. Your Pydantic AI agent uses this structured data to determine which team should handle complex customer inquiries. Because every Aidbase field is strictly typed, your Pydantic AI routing algorithms can trust the output implicitly. You write clean, assertion-free Python code that executes reliably under heavy support loads.

Setup guide

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

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

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

It eliminates silent data corruption by enforcing strict runtime type-checking on every API response. Tools like list_aidbase_knowledge map directly to Pydantic models, so you know your agent is working with clean data.

You initialize the MCPToolset with your Vinkius HTTP endpoint URL. Pass this toolset directly to your Agent constructor to let your model run commands like send_aidbase_reply safely.

The framework catches the schema mismatch instantly and raises a validation error. This prevents your LLM from hallucinating arguments or writing corrupted data back to your support desk.

Yes, you can run the server externally and use mock data to test your tool calls. Since the types are hardcoded in your Pydantic schemas, your local tests will perfectly match production behavior.

All data payloads are processed in memory within an isolated V8 sandbox and immediately purged upon completion. No customer replies are stored on disk, preventing unauthorized access to your private communication logs.

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