Why do I get an error when providing my token?

Tettra's API keys are exclusively available to workspaces on their **Scaling** or **Professional** subscription tiers. If your team operates on a free or basic plan, the API credentials menu will not be accessible and requests will be blocked.

Can the AI rewrite existing company wiki articles?

Yes. Using the `update_wiki_page` function, the AI can overwrite existing body content and titles. It adopts your user profile's access permissions, meaning it can only update pages you personally have edit rights for in the Tettra UI.

Where do I track down my Tettra Team ID?

Your Team ID is the slug prefix used in your Tettra domain. For example, if you access your wiki primarily through `https://app.tettra.co/teams/acme-corp`, your Team ID is exactly `acme-corp`.

Tettra MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Tettra
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Tettra through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Tettra "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Tettra?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Tettra MCP Server

Connect your Tettra internal knowledge base to any AI agent and bring your company's documentation directly into your developer workflow. No more switching tabs to look up API specs or onboarding guides.

Pydantic AI validates every Tettra tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Deep Search — Perform full-text searches across all your company's Tettra pages to instantly find answers and organizational knowledge
Knowledge Retrieval — Read the complete markdown/HTML content of any page, technical guide, or team policy natively inside your chat
Content Creation — Command your agent to draft and publish new wiki pages, or suggest documentation updates on the fly
Category Navigation — Browse through your team's top-level categories, root folders, and subcategories visually
Q&A Management — Post new questions to your team's internal Q&A board or list unanswered questions right from your IDE

The Tettra MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Tettra to Pydantic AI via MCP

Follow these steps to integrate the Tettra MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Tettra with type-safe schemas

Why Use Pydantic AI with the Tettra MCP Server

Pydantic AI provides unique advantages when paired with Tettra through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Tettra integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Tettra connection logic from agent behavior for testable, maintainable code

Tettra + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Tettra MCP Server delivers measurable value.

Type-safe data pipelines: query Tettra with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Tettra tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Tettra and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Tettra responses and write comprehensive agent tests

Tettra MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Tettra to Pydantic AI via MCP:

create_qa_question

Posts a new question in the Tettra Q&A system

create_wiki_page

Provide title, content, and category ID. Creates a new wiki page in a specific category

get_category_details

Retrieves details for a specific Tettra category

get_page_content

Returns title and Markdown/HTML body. Retrieves the full content and metadata of a specific Tettra page

list_categories

Lists all top-level categories in the Tettra wiki

list_pages_in_category

Lists all wiki pages within a specific category

list_qa_questions

Lists all questions posted in the Tettra Q&A system

list_subcategories

Lists all subcategories under a specific parent category

search_pages

Returns up to 5 matching pages. Full-text search across all Tettra wiki pages

suggest_new_page

Suggests a new wiki page to the team

update_wiki_page

Provide the page ID and the new fields. Updates the title or content of an existing Tettra page

verify_wiki_page

Marks a Tettra page as verified and up-to-date

Example Prompts for Tettra in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Tettra immediately.

"Search the wiki for 'Database Migration Checklist'."

"Create a new wiki page in the 'Support' category explaining how to handle refund requests."

"Mark page ID 883 as verified and up to date."

Troubleshooting Tettra MCP Server with Pydantic AI

Common issues when connecting Tettra to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Tettra + Pydantic AI FAQ

Common questions about integrating Tettra MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Tettra MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.