How to Use the Retable MCP in Pydantic AI

Build type-safe Pydantic AI agents that query and write to Retable with strict runtime validation and zero silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Retable MCP to Pydantic AI

Create your Vinkius account to connect Retable 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 Retable with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Record Retrieval

The `get_record` tool fetches specific row data and passes it directly into your agent's validation pipeline. If you need to inspect multiple entries, `list_records` pulls the dataset for batch processing. Because Pydantic AI enforces type safety, any unexpected data format returned from the MCP Server triggers an immediate validation error. This prevents corrupted or misaligned data from feeding into your LLM loops.

Map workspaces securely using this MCP Server

The `list_projects` tool returns the workspaces your API key can access, allowing your agent to locate the correct dataset. To drill down further, the agent calls `list_tables` to see the available sheets in that project. The agent uses `get_project` and `get_table` to inspect structural metadata. This structural mapping ensures your agent knows the exact schema of the relational tables before it attempts to write any new data.

Execute validated database writes and updates

The `create_record` tool writes new rows to your sheets, while `update_record` modifies existing fields. Every write payload is validated against your Pydantic models before the API call is made. For managing the lifecycle of your rows, the agent can use `delete_record` to purge old entries. This ensures your active MCP session only interacts with clean, verified data, while `check_retable_status` makes sure the API is responsive before initiating these database mutations.

Setup guide

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

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

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

Use the MCPToolset class pointing to your Vinkius server URL and pass it to the agent's toolsets argument. This registers all ten database tools, making them instantly available to your model.

The agent will raise a validation error instantly. This prevents your model from hallucinating or operating on bad data, which is a key advantage of using this type-safe setup.

No. The server focuses on data operations and structure discovery. It uses `list_tables` and `get_table` to read schemas, but does not support creating or deleting tables.

No. Vinkius manages the server hosting. Your agent connects to the external Vinkius HTTP endpoint, so you do not have to manage any local server processes.

All data transit is encrypted, and Vinkius runs the server in an ephemeral sandbox. Your Retable spreadsheet records and API keys are never saved or logged, ensuring complete data privacy.

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