How do I perform an ANN search through my agent?

Use the `search_vectors` tool by providing the collection name and a JSON float array matching the collection's dimensions. Your agent will perform an Approximate Nearest Neighbor search and return the most semantically relevant entities.

Can I filter results using structured fields instead of just vectors?

Yes. Use the `query_entities` tool with a Milvus-style filter expression. This allows you to retrieve entities based on primary keys, tags, or other scalar fields without necessarily performing a vector similarity search.

How do I check the schema and dimension requirements for a Milvus collection?

The `describe_collection` tool retrieves the complete schema mapping. Your agent will report the required vector dimensions, index types, and primary key names, helping you ensure your search queries are compatible with the database logic.

Milvus (Open-Source Vector Database) MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Milvus (Open-Source Vector Database)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Milvus (Open-Source Vector Database)?"
    )
    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 Milvus (Open-Source Vector Database) MCP Server

Connect your Milvus instance to any AI agent and take full control of your high-performance vector search, embedding storage, and scalar data management through natural conversation.

Pydantic AI validates every Milvus (Open-Source Vector Database) tool response against typed schemas, catching data inconsistencies at build time. Connect 7 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

Vector Search Orchestration — Execute Approximate Nearest Neighbor (ANN) searches against your collections by providing raw embedding vectors to retrieve semantically relevant matches directly from your agent
Scalar Query Filters — Use sophisticated scalar expressions to filter entities by structured fields (e.g., tags, IDs, dates) alongside your vector search for precise data retrieval
Collection Lifecycle Audit — List all managed vector collections and retrieve detailed schema definitions, including dimensions, primary keys, and index types natively
Performance Statistics — Extract real-time metrics for your collections, including entity counts and physical memory usage, to monitor the health of your vector store
Precision Retrieval — Fetch specific vector items by their primary keys, bypassing standard semantic boundaries to audit exact data points securely
Data Management — Irreversibly delete specific vector records using primary identifiers to maintain a clean and optimized search index across your Milvus instance

The Milvus (Open-Source Vector Database) MCP Server exposes 7 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 Milvus (Open-Source Vector Database) to Pydantic AI via MCP

Follow these steps to integrate the Milvus (Open-Source Vector Database) 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 7 tools from Milvus (Open-Source Vector Database) with type-safe schemas

Why Use Pydantic AI with the Milvus (Open-Source Vector Database) MCP Server

Pydantic AI provides unique advantages when paired with Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) integration code

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

Dependency injection system cleanly separates your Milvus (Open-Source Vector Database) connection logic from agent behavior for testable, maintainable code

Milvus (Open-Source Vector Database) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Milvus (Open-Source Vector Database) MCP Server delivers measurable value.

Type-safe data pipelines: query Milvus (Open-Source Vector Database) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Milvus (Open-Source Vector Database) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Milvus (Open-Source Vector Database) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Milvus (Open-Source Vector Database) responses and write comprehensive agent tests

Milvus (Open-Source Vector Database) MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Milvus (Open-Source Vector Database) to Pydantic AI via MCP:

delete_entities

Irreversibly delete specific vector records utilizing primary keys

describe_collection

Explore the explicit schema mapping and indexing definition of a Milvus collection

get_collection_stats

Get collection statistics bounding row counts natively

get_entities

Extract unique vector items bounding exactly by known Primary Keys

list_collections

Always query this first. List index collections tracked inside the Milvus Vector Database

query_entities

Query explicitly using scalar expressions to retrieve entities

search_vectors

Make sure to feed a strict explicit JSON Array matching exact dimensions. Search nearest vector neighbors matching implicit embedding inputs

Example Prompts for Milvus (Open-Source Vector Database) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Milvus (Open-Source Vector Database) immediately.

"List all vector collections in my Milvus instance"

"Search collection 'text_knowledge_base' for vector: [0.1, -0.2, ...]"

"Show me the row count and memory stats for collection 'image_embeddings'"

Troubleshooting Milvus (Open-Source Vector Database) MCP Server with Pydantic AI

Common issues when connecting Milvus (Open-Source Vector Database) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Milvus (Open-Source Vector Database) + Pydantic AI FAQ

Common questions about integrating Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.