How to Use the Tettra MCP in Pydantic AI

Q: How does Tettra's knowledge base integrate with Pydantic AI?

The MCP Server provides tools like getpagecontent and searchpages. Your agent uses these, but Pydantic validates the resulting data structure at runtime. This means you get clean, predictable objects every time.

Q: Can I manage page structure with Tettra using Pydantic AI?

Yes. The agent can list categories via listcategories and validate sub-sections through listsubcategories. This makes mapping the entire knowledge domain a predictable, type-checked process.

Q: What happens if I need to update a Tettra page using Pydantic AI?

The agent calls updatewikipage with the ID and new fields. If the incoming data doesn't match your schema, the process fails immediately with a clear validation error—no silent corruption.

Interact with Tettra's knowledge base using strict data validation via Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tettra MCP to Pydantic AI

Create your Vinkius account to connect Tettra 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 Tettra with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and retrieve structured document data.

When your agent needs to find a specific process, it uses `search_pages` to get up to five matching Tettra wiki pages. Because of Pydantic's validation, the response fields are guaranteed to match expected types—no unexpected keys. Need more context? Use `get_page_content` for a full download of the title and body content. The agent can then parse this structured data into defined Python models.

Manage wiki structure with type safety.

Before creating something, your agent verifies where it belongs. Call `list_categories` to get a validated list of all top-level sections. This ensures that when you use `create_wiki_page`, the category ID passed is valid and expected by the schema. It also lets the agent map out sub-sections using `list_subcategories`. The whole process remains type-safe, preventing runtime errors from malformed data.

Control content creation and revision history.

When a team finalizes a document, your agent uses `create_wiki_page` to commit the record. This structured approach guarantees that all required fields—title, body, category ID—are present before the page is written. If revisions happen, use `update_wiki_page`. Pydantic ensures that even if only a small part of the content changes, the resulting object still adheres to your defined schema.

Setup guide

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

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

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

The MCP Server provides tools like `get_page_content` and `search_pages`. Your agent uses these, but Pydantic validates the resulting data structure at runtime. This means you get clean, predictable objects every time.

Yes. The agent can list categories via `list_categories` and validate sub-sections through `list_subcategories`. This makes mapping the entire knowledge domain a predictable, type-checked process.

The agent calls `update_wiki_page` with the ID and new fields. If the incoming data doesn't match your schema, the process fails immediately with a clear validation error—no silent corruption.

By forcing all MCP responses through Pydantic models. This guardrail mechanism validates the structure of every piece of returned metadata, making your agent reliable for production use.

This server handles internal wiki pages (Markdown/HTML body content) and structured Q&A question records. The focus is on ensuring the metadata surrounding these texts is always correct.

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