How to Use the ThinkStack MCP in Pydantic AI

Q: How do I audit data integrity with ThinkStack and Pydantic AI?

Every interaction is auditable. You use listconversations to get a log, and since Pydantic validates the output of every tool call, you know that historical record hasn't corrupted.

Q: What tools are available for managing knowledge sources with ThinkStack and Pydantic AI?

You can manage sources using addsource to ingest data or deletesource to remove it. Always confirm your inventory by calling listsources first.

Q: Can I list all available bots using ThinkStack and Pydantic AI?

Yeah, listbots gives you a roster of everything. If you need specifics on one bot's configuration or actions, use getbot or listactions, respectively.

Guarantee correct outputs with Pydantic AI: Type-safe bot management via ThinkStack MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to Pydantic AI

Create your Vinkius account to connect ThinkStack to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ThinkStack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate all agent responses

`send_query` sends the prompt, but critically, the response is validated against a schema. If the data returned by `send_query` doesn't match your Pydantic model, the agent fails loud—you know exactly what broke. This guarantees that the output from any query is correct and structured for immediate use in subsequent code.

Manage source data contracts

You control what knowledge the bot sees using `add_source` and `delete_source`. These tools ensure your underlying documentation adheres to defined ingestion rules. Always run `list_sources` first; it lets you check the structure of the content before adding anything sensitive.

Audit bot capabilities and history

`get_bot` pulls specific, structured data about a chatbot's configuration. Meanwhile, `list_actions` provides an explicit list of available functions for the agent to call. If you need historical context, use `list_conversations`, which returns conversation records that must pass validation.

Setup guide

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

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

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

Every interaction is auditable. You use `list_conversations` to get a log, and since Pydantic validates the output of every tool call, you know that historical record hasn't corrupted.

You can manage sources using `add_source` to ingest data or `delete_source` to remove it. Always confirm your inventory by calling `list_sources` first.

This server handles conversation details, meaning the data includes full chat history and user inputs. Since validation is key here, every piece of this information must be structured correctly for compliance.

Yeah, `list_bots` gives you a roster of everything. If you need specifics on one bot's configuration or actions, use `get_bot` or `list_actions`, respectively.

Yes, that’s the whole point. Because of the runtime validation layer, every single MCP Server response must match a predefined Pydantic schema. You'll never get junk data.

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