How to Use the Milvus (Open-Source Vector Database) MCP in Pydantic AI

Q: How does Pydantic AI validate responses from Milvus (Open-Source Vector Database)?

The framework intercepts the output of tools like getentities and parses them through Pydantic models. If the database returns a field that doesn't match your schema, it raises a runtime validation error.

Run type-safe vector queries on Milvus (Open-Source Vector Database) with runtime validation using Pydantic AI and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Milvus (Open-Source Vector Database) MCP to Pydantic AI

Create your Vinkius account to connect Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe vector search with Pydantic AI

This MCP Server exposes `search_vectors` to query your vector embeddings with strict type validation on every response. Pydantic AI validates the returned coordinate arrays and similarity scores against Python models before your agent can use them. If the database returns unexpected fields or malformed data, the framework raises a validation error immediately. This prevents silent failures in production and guarantees your application logic only receives clean data.

Inspect collection structures with type guarantees

Run `describe_collection` to inspect the schema layout and index types of your target collection. The returned schema is validated at runtime, ensuring your agent knows the exact field names and data types. Your agent uses `list_collections` to discover active tables without risking hallucinated table names. This direct mapping allows the agent to safely route queries to the correct vector index.

Query and delete entities with strict validation

Run `query_entities` to filter your records using scalar expressions with validated outputs. If you need to remove stale data, calling `delete_entities` via MCP ensures your primary keys conform to the expected format before the request goes out. You can also fetch specific records by their IDs using `get_entities`. Every single record returned is parsed through Pydantic, giving you absolute certainty that the data structure matches your codebase.

Setup guide

Set up Milvus (Open-Source Vector Database) 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": {
        "milvus-open-source-vector-database-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Milvus (Open-Source Vector Database) 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 Milvus. 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 Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) MCP in Pydantic AI

The framework intercepts the output of tools like `get_entities` and parses them through Pydantic models. If the database returns a field that doesn't match your schema, it raises a runtime validation error.

Yes. The framework is model-agnostic, meaning you can run your type-safe vector queries using OpenAI, Anthropic, or local models.

You initialize the toolset with the Vinkius HTTP endpoint URL. You then pass this toolset directly to your Agent constructor to expose tools like `search_vectors` over MCP.

Pydantic AI validates the structure of the stats payload. If the server returns empty metrics, the validation layer safely handles the missing fields based on your model's optional types.

Your scalar metadata and primary keys are validated locally within your Python runtime. The Vinkius MCP Server handles database connections within an isolated sandbox, keeping your credentials and data secure.

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