How to Use the Verba MCP in Pydantic AI

Q: What is the best way to use Verba with Pydantic AI?

Use performragquery for reliable answers. Because the output is typed, you can immediately pass that data into subsequent functions without worrying about its format.

Q: If I add a new document using Verba with Pydantic AI, how do I know it worked?

You check the knowledge base status by calling listknowledgedocuments. The agent confirms that the item count increased and the data structure is correct.

Q: What happens if a document detail retrieved via Verba with Pydantic AI is wrong?

Since all responses are type-checked, if getdocumentdetails returns malformed content, your agent fails the validation step immediately. You know exactly where the data problem is.

Guaranteed correct outputs for production agents using Pydantic AI and Verba 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 Verba MCP to Pydantic AI

Create your Vinkius account to connect Verba 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 Verba with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute type-safe knowledge querying.

You run `perform_rag_query` to get answers, but unlike other methods, the response is validated against Pydantic models. This means if Verba returns something unexpected, your agent fails loudly with a validation error—no silent corruption. It’s perfect for correctness-first applications where hallucinated or malformed data simply isn't an option.

Maintain verifiable knowledge sources.

When you need to upload content, use `add_knowledge_document`. This ensures the source document and its metadata JSON are properly indexed. For maintenance, `delete_knowledge_document` removes data permanently—the agent knows exactly what it's deleting. This gives you total control over the knowledge base used by your typed Python framework.

Inspect system state with guaranteed structure.

Need to know what rules are in place? Call `get_system_config`. The result is validated against Pydantic, so you get a structured object, not just a text blob. Similarly, checking details via `get_document_details` yields predictable data. These tools provide operational certainty that other MCP Servers can't match.

Setup guide

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

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

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

Every time the Verba MCP Server returns a value, your agent validates it against the schema you define. This prevents unexpected fields or bad formats from corrupting your workflow.

Use `perform_rag_query` for reliable answers. Because the output is typed, you can immediately pass that data into subsequent functions without worrying about its format.

You check the knowledge base status by calling `list_knowledge_documents`. The agent confirms that the item count increased and the data structure is correct.

Since all responses are type-checked, if `get_document_details` returns malformed content, your agent fails the validation step immediately. You know exactly where the data problem is.

The server manages document content and associated metadata JSON. The value here is that this information is always passed through a strict, type-safe validation layer.

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