ThinkStack MCP Server for Pydantic AIGive Pydantic AI instant access to 10 tools to Add Source, Check Thinkstack Status, Delete Source, and more
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ThinkStack through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this App Connector for Pydantic AI
The ThinkStack app connector for Pydantic AI is a standout in the Productivity category — giving your AI agent 10 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
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 ThinkStack "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in ThinkStack?"
)
print(result.data)
asyncio.run(main())
* 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 ThinkStack MCP Server
Connect your ThinkStack account to any AI agent and manage your chatbots, knowledge bases, and conversations through natural language.
Pydantic AI validates every ThinkStack tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through 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
- Chatbot Management u2014 List and configure all AI chatbots in your account
- Knowledge Base u2014 Add, list, and remove knowledge sources (URLs, documents) for any chatbot
- Live Queries u2014 Send messages to your chatbots and receive AI-generated responses in real time
- Conversation History u2014 Review all chat sessions with full message history and user metadata
- Actions & Webhooks u2014 View all configured REST API actions for your chatbots
The ThinkStack MCP Server exposes 10 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.
All 10 ThinkStack tools available for Pydantic AI
When Pydantic AI connects to ThinkStack through Vinkius, your AI agent gets direct access to every tool listed below — spanning thinkstack, chatbot-api, ai-manage, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
The content will be crawled and indexed automatically. Add a knowledge source
Verify ThinkStack API connectivity
Remove a knowledge source
Get chatbot details
Get conversation details
List bot actions
List all chatbots
List conversations
List knowledge sources
Query a chatbot
Connect ThinkStack to Pydantic AI via MCP
Follow these steps to wire ThinkStack into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the ThinkStack MCP Server
Pydantic AI provides unique advantages when paired with ThinkStack 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 ThinkStack integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your ThinkStack connection logic from agent behavior for testable, maintainable code
ThinkStack + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the ThinkStack MCP Server delivers measurable value.
Type-safe data pipelines: query ThinkStack with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple ThinkStack tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query ThinkStack and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock ThinkStack responses and write comprehensive agent tests
Example Prompts for ThinkStack in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with ThinkStack immediately.
"List all my chatbots in ThinkStack."
"Ask my Support Bot: 'How do I reset my password?'"
"Add docs.example.com as a knowledge source for my Sales bot."
Troubleshooting ThinkStack MCP Server with Pydantic AI
Common issues when connecting ThinkStack to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiThinkStack + Pydantic AI FAQ
Common questions about integrating ThinkStack MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.