How to Use the Knack MCP in Pydantic AI

Q: Can Pydantic AI handle Knack's custom field keys?

Yes. The agent calls listobjectfields to discover keys like field42 dynamically, then maps them to your readable Python models using standard Pydantic aliases.

Connect Knack to Pydantic AI to enforce strict type validation on every database read, write, and schema discovery operation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knack MCP to Pydantic AI

Create your Vinkius account to connect Knack 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 Knack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover and validate schemas at runtime

The `get_object_schema` tool pulls the raw metadata for any table so your Pydantic AI agent knows exactly what it is dealing with. It checks the object name and key before executing any downstream logic. Next, `list_object_fields` grabs the actual column definitions. Since you use Pydantic, unexpected API responses trigger an immediate validation error. Your agent fails loudly instead of silently corrupting your sync pipeline when a field type changes.

Execute precise database writes

The `create_record` tool pushes new entries into your database using a strictly formatted JSON string. Your agent validates the payload against your Pydantic models first, ensuring no missing required fields make it to the API. For existing data, `update_record` handles partial modifications. The agent constructs the JSON payload containing only the modified fields, executes the tool, and maps the response back into a strictly typed Python object.

Query the Knack MCP Server safely

The `get_record` tool fetches a single row by its exact ID through the Knack MCP Server. This guarantees you are auditing the correct entry, pulling the raw data straight into your validated models. When you need to find multiple rows, `search_records` accepts standard Knack Filter format JSON. Your agent constructs the filter array safely, queries the database, and parses the results into typed structures you can actually trust in production.

Setup guide

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

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

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

Use the MCPToolset class with your HTTP endpoint URL. Pass this toolset into your Agent constructor. The older MCPServerHTTP class is deprecated.

It guarantees data correctness. If Knack returns a string where you expect an integer, Pydantic AI throws a validation error immediately. You catch schema drift before it ruins your data.

Yes. The agent calls list_object_fields to discover keys like field_42 dynamically, then maps them to your readable Python models using standard Pydantic aliases.

The MCP Server itself is model-agnostic. As long as your Python setup can route tool calls, you can use local models, Anthropic, or OpenAI to execute the database operations.

The integration reads your table structures and raw row values. This data moves over an encrypted connection directly to your Python runtime, with zero persistence in the MCP layer.

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