How to Use the Jestor MCP in Pydantic AI

Q: How do I set up the Jestor toolset in Pydantic AI?

Begin by installing the package with pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class initialized with your Vinkius URL, then pass it to your Agent via the toolsets argument.

Q: Can I use Pydantic AI to inspect Jestor database schemas?

Your agent can easily call listobjects to see available tables, and then use getobject to inspect specific field types. The returned schemas are parsed and validated by the framework so the agent can reason about them safely.

Build type-safe Python agents that validate every Jestor record and schema at runtime using this 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 Jestor MCP to Pydantic AI

Create your Vinkius account to connect Jestor 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 Jestor with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent silent database errors with strict runtime validation

Pydantic AI is built for developers who hate silent failures. When your agent calls `get_record` or `list_records`, the incoming data is instantly validated against strict Pydantic schemas. If a field type changes or a database record returns unexpected nulls, the framework raises a loud validation error immediately. This prevents corrupted data from slipping into your downstream production systems. You get absolute certainty that the data your agent processes matches your application's expectations. It is the cleanest way to run LLMs against a dynamic database without losing sleep over type safety.

Audit system automation using type-safe MCP Server tools

Auditing complex backend configurations requires absolute precision. By using `list_workflows` and `list_webhooks`, your agent can fetch active system logic and parse it into structured Python models. The framework ensures that every webhook URL and workflow trigger matches the expected format before the agent analyzes it. Running these checks ensures compliance without manual overhead. The agent can safely check your setup, run `get_me` to verify its own permissions, and output clean, structured reports. There is no risk of the agent hallucinating fields because the schemas are locked down at runtime.

Unified toolset configuration for multi-model agents

Pydantic AI uses a clean, unified configuration approach that makes setting up your server incredibly simple. Just run `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius HTTP endpoint. Note that the older `MCPServerHTTP` class is deprecated, so you will want to use the new unified toolset class. Once initialized, pass the toolset directly to your Agent constructor. This single setup works across OpenAI, Anthropic, Gemini, or local models. Your agent instantly gains the ability to query `list_objects` and `list_dashboards` using either Streamable HTTP or SSE transports.

Setup guide

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

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

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

Begin by installing the package with `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class initialized with your Vinkius URL, then pass it to your Agent via the `toolsets` argument.

Pydantic AI will catch the mismatch immediately at runtime. If a tool like `get_record` returns a field that violates your model's type definitions, the framework raises a validation error rather than letting the agent proceed with bad data.

Both transport protocols are fully supported by the Vinkius-hosted server. You can configure your Pydantic AI client to connect via Server-Sent Events or standard HTTP streaming based on your network architecture.

Your agent can easily call `list_objects` to see available tables, and then use `get_object` to inspect specific field types. The returned schemas are parsed and validated by the framework so the agent can reason about them safely.

Your connection metadata and API keys are isolated within Vinkius's secure V8 sandboxes. When the agent uses the MCP Server to call `get_me` to check its status, the authentication handshake is handled externally by Vinkius, ensuring your raw API tokens are never exposed to the LLM or stored in client-side logs.

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