Can my AI agent write complex GROQ queries for me?

Yes. If you know what data you want but aren't totally familiar with GROQ syntax, you can simply ask your agent: 'Write and execute a GROQ query to find all author documents where the name starts with John and return just their ID and bio.' The agent will draft the query, execute it via the `run_groq_query` tool, and return the filtered JSON.

How do I perform a bulk update on my documents?

You can ask your agent to first fetch the documents (e.g., 'List all posts missing a category'), calculate the changes needed, and then use the `run_raw_mutation` tool or `patch_cms_document` iteratively to apply the updates. This acts as a conversational migration script, updating dozens of documents safely and quickly.

Can the agent check if media assets are missing from my posts?

Yes. The agent can use the document querying tools combined with `list_media_assets` to analyze your content. For instance, you can ask it to generate a report of all products that do not have an associated image reference, giving you an exact list of items to fix in the Studio.

Sanity MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Sanity
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Sanity through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Sanity "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Sanity?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Sanity MCP Server

Connect your Sanity project to any AI agent and take full control of your Content Lake through natural conversation.

Pydantic AI validates every Sanity 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

GROQ Queries — Execute powerful Graph-Relational Object Queries to fetch exactly the content you need
Document Management — Create, read, update, patch, and delete documents of any schema type
Schema Insights — List unique schema types and count entity nodes dynamically
Media Assets — Browse and manage images and file assets uploaded to your project
Bulk Operations — Run raw Sanity mutations for complex, multi-document transactions

The Sanity 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.

How to Connect Sanity to Pydantic AI via MCP

Follow these steps to integrate the Sanity MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Sanity with type-safe schemas

Why Use Pydantic AI with the Sanity MCP Server

Pydantic AI provides unique advantages when paired with Sanity 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 Sanity integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Sanity connection logic from agent behavior for testable, maintainable code

Sanity + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Sanity MCP Server delivers measurable value.

Type-safe data pipelines: query Sanity with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Sanity tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Sanity and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Sanity responses and write comprehensive agent tests

Sanity MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Sanity to Pydantic AI via MCP:

count_entity_nodes

Counts the number of documents of a specific type

create_cms_document

Specify the type and provide attributes as a JSON object. Creates a new document in the CMS

get_document_details

Retrieves full details for a specific document by ID

list_media_assets

Lists all image and file assets uploaded to Sanity

list_typed_documents

g., "post", "author"). Lists all documents of a specific type

list_unique_schema_types

Retrieves a list of all unique document types present in the dataset

patch_cms_document

Provide a JSON object of fields to set. Updates specific fields of an existing document

run_groq_query

Executes a GROQ (Graph-Relational Object Queries) query

run_raw_mutation

Provide a JSON array of mutation objects. Executes a raw Sanity mutation

wipe_cms_document

This action is irreversible. Permanently deletes a document from the CMS

Example Prompts for Sanity in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Sanity immediately.

"List all unique schema types in my dataset."

"Write a GROQ query to find the 3 most recently updated authors."

"Update the post with ID 'drafts.1234' and set its published state to true."

Troubleshooting Sanity MCP Server with Pydantic AI

Common issues when connecting Sanity to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Sanity + Pydantic AI FAQ

Common questions about integrating Sanity MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Sanity MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.