MCP Server for Milvus

> The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

This repository contains a MCP server that provides access to Milvus vector database functionality.

Prerequisites

Before using this MCP server, ensure you have:

• Python 3.10 or higher
• A running Milvus instance (local or remote)
• uv installed (recommended for running the server)

Usage

The recommended way to use this MCP server is to run it directly with `uv` without installation. This is how both Claude Desktop and Cursor are configured to use it in the examples below.

If you want to clone the repository:

git clone https://github.com/zilliztech/mcp-server-milvus.git
cd mcp-server-milvus

Then you can run the server directly:

uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530

Alternatively you can change the .env file in the `src/mcp_server_milvus/` directory to set the environment variables and run the server with the following command:

uv run src/mcp_server_milvus/server.py

Important: the .env file will have higher priority than the command line arguments.

Running Modes

The server supports two running modes: stdio (default) and SSE (Server-Sent Events).

Stdio Mode (Default)

• Description: Communicates with the client via standard input/output. This is the default mode if no mode is specified.

• Usage:

uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530

SSE Mode

• Description: Uses HTTP Server-Sent Events for communication. This mode allows multiple clients to connect via HTTP and is suitable for web-based applications.

• Usage:

uv run src/mcp_server_milvus/server.py --sse --milvus-uri http://localhost:19530 --port 8000

• Debugging in SSE Mode:

If you want to debug in SSE mode, after starting the SSE service, enter the following command:

mcp dev src/mcp_server_milvus/server.py

The output will be similar to:

% mcp dev src/mcp_server_milvus/merged_server.py
  Starting MCP inspector...
  ⚙️ Proxy server listening on port 6277
  🔍 MCP Inspector is up and running at http://127.0.0.1:6274 🚀

You can then access the MCP Inspector at `http://127.0.0.1:6274` for testing.

Streamable HTTP Mode

• Description: Uses HTTP with streaming support for communication. This is the recommended transport for production deployments and supports both stateful and stateless operation.

• Usage:

uv run src/mcp_server_milvus/server.py --streamable-http --milvus-uri http://localhost:19530 --port 8000

• Stateless Mode:

uv run src/mcp_server_milvus/server.py --streamable-http --stateless --milvus-uri http://localhost:19530 --port 8000

Supported Applications

This MCP server can be used with various LLM applications that support the Model Context Protocol:

• Claude Desktop: Anthropic's desktop application for Claude
• Cursor: AI-powered code editor with MCP support
• Custom MCP clients: Any application implementing the MCP client specification

Usage with Claude Desktop

Configuration for Different Modes

SSE Mode Configuration

Follow these steps to configure Claude Desktop for SSE mode:

1. Install Claude Desktop from https://claude.ai/download.

2. Open your Claude Desktop configuration file:

3. Add the following configuration for SSE mode:

{
  "mcpServers": {
    "milvus-sse": {
      "url": "http://your_sse_host:port/sse",
      "disabled": false,
      "autoApprove": []
    }
  }
}

Streamable HTTP Mode Configuration

{
  "mcpServers": {
    "milvus-streamable-http": {
      "url": "http://your_host:port/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}

4. Restart Claude Desktop to apply the changes.

Stdio Mode Configuration

For stdio mode, follow these steps:

1. Install Claude Desktop from https://claude.ai/download.

2. Open your Claude Desktop configuration file:

3. Add the following configuration for stdio mode:

{
  "mcpServers": {
    "milvus": {
      "command": "/PATH/TO/uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-milvus/src/mcp_server_milvus",
        "run",
        "server.py",
        "--milvus-uri",
        "http://localhost:19530"
      ]
    }
  }
}

4. Restart Claude Desktop to apply the changes.

Usage with Cursor

Cursor also supports MCP tools. You can integrate your Milvus MCP server with Cursor by following these steps:

Integration Steps

1. Open `Cursor Settings` > `MCP`

2. Click on `Add new global MCP server`

3. After clicking, it will automatically redirect you to the `mcp.json` file, which will be created if it doesn’t exist

Configuring the `mcp.json` File

For Stdio Mode:

Overwrite the `mcp.json` file with the following content:

{
  "mcpServers": {
    "milvus": {
      "command": "/PATH/TO/uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-milvus/src/mcp_server_milvus",
        "run",
        "server.py",
        "--milvus-uri",
        "http://127.0.0.1:19530"
      ]
    }
  }
}

For SSE Mode:

1. Start the service by running the following command:

uv run src/mcp_server_milvus/server.py --sse --milvus-uri http://your_sse_host --port port

> Note: Replace `http://your_sse_host` with your actual SSE host address and `port` with the specific port number you’re using.

2. Once the service is up and running, overwrite the `mcp.json` file with the following content:

{
       "mcpServers": {
         "milvus-sse": {
           "url": "http://your_sse_host:port/sse",
           "disabled": false,
           "autoApprove": []
         }
       }
   }

For Streamable HTTP Mode:

1. Start the service:

uv run src/mcp_server_milvus/server.py --streamable-http --milvus-uri http://your_host --port port

2. Update `mcp.json`:

{
     "mcpServers": {
       "milvus-streamable-http": {
         "url": "http://your_host:port/mcp",
         "disabled": false,
         "autoApprove": []
       }
     }
   }

Completing the Integration

After completing the above steps, restart Cursor or reload the window to ensure the configuration takes effect.

Verifying the Integration

To verify that Cursor has successfully integrated with your Milvus MCP server:

1. Open `Cursor Settings` > `MCP`

2. Check if "milvus", "milvus-sse", or "milvus-streamable-http" appear in the list (depending on the mode you have chosen)

3. Confirm that the relevant tools are listed (e.g., milvus_list_collections, milvus_vector_search, etc.)

4. If the server is enabled but shows an error, check the Troubleshooting section below

Available Tools

The server provides the following tools:

Search and Query Operations

• `milvus_text_search`: Search for documents using full text search

• `milvus_vector_search`: Perform vector similarity search on a collection
  • Parameters:
    • `collection_name`: Name of collection to search
    • `vector`: Query vector
    • `vector_field`: Field name for vector search (default: "vector")
    • `limit`: The maximum number of results to return (default: 5)
    • `output_fields`: Fields to include in results
    • `filter_expr`: Filter expression
    • `metric_type`: Distance metric (COSINE, L2, IP) (default: "COSINE")
    • `radius`: Optional lower bound for range search (default: None)
    • `range_filter`: Optional upper bound for range search (default: None)
• `milvus_hybrid_search`: Perform hybrid search on a collection
  • Parameters:
    • `collection_name`: Name of collection to search
    • `query_text`: Text query for search
    • `text_field`: Field name for text search
    • `vector`: Vector of the text query
    • `vector_field`: Field name for vector search
    • `limit`: The maximum number of results to return (default: 5)
    • `output_fields`: Fields to include in results
    • `filter_expr`: Filter expression
    • `sparse_radius`: Optional lower bound for sparse range search (default: None)
    • `sparse_range_filter`: Optional upper bound for sparse range search (default: None)
    • `dense_radius`: Optional lower bound for dense range search (default: None)
    • `dense_range_filter`: Optional upper bound for dense range search (default: None)
• `milvus_text_similarity_search`: Perform text similarity search on a collection

> Note: This tool is only supported in Milvus 2.6.0 and above. And you need to set the embedding function at the Milvus server. See Embedding Function for more details.

• `milvus_query`: Query collection using filter expressions
  • Parameters:
    • `collection_name`: Name of collection to query
    • `filter_expr`: Filter expression (e.g. 'age > 20')
    • `output_fields`: Fields to include in results
    • `limit`: The maximum number of results to return (default: 10)

Collection Management

• `milvus_list_collections`: List all collections in the database

• `milvus_create_collection`: Create a new collection with quick setup or customized schema

• `milvus_load_collection`: Load a collection into memory for search and query

• `milvus_release_collection`: Release a collection from memory
  • Parameters:
    • `collection_name`: Name of collection to release

• `milvus_get_collection_info`: Lists detailed information like schema, properties, collection ID, and other metadata of a specific collection.
  • Parameters:
    • `collection_name`: Name of the collection to get detailed information about

Data Operations

• `milvus_insert_data`: Insert data into a collection

• `milvus_delete_entities`: Delete entities from a collection based on filter expression
  • Parameters:
    • `collection_name`: Name of collection
    • `filter_expr`: Filter expression to select entities to delete

Environment Variables

• `MILVUS_URI`: Milvus server URI (can be set instead of --milvus-uri)
• `MILVUS_TOKEN`: Optional authentication token
• `MILVUS_DB`: Database name (defaults to "default")

Development

To run the server directly:

uv run server.py --milvus-uri http://localhost:19530

Examples

Using Claude Desktop

Example 1: Listing Collections

What are the collections I have in my Milvus DB?

Claude will then use MCP to check this information on your Milvus DB.

I'll check what collections are available in your Milvus database.

Here are the collections in your Milvus database:

1. rag_demo
2. test
3. chat_messages
4. text_collection
5. image_collection
6. customized_setup
7. streaming_rag_demo

Example 2: Searching for Documents

Find documents in my text_collection that mention "machine learning"

Claude will use the full-text search capabilities of Milvus to find relevant documents:

I'll search for documents about machine learning in your text_collection.

> View result from milvus-text-search from milvus (local)

Here are the documents I found that mention machine learning:
[Results will appear here based on your actual data]

Using Cursor

Example: Creating a Collection

In Cursor, you can ask:

Create a new collection called 'articles' in Milvus with fields for title (string), content (string), and a vector field (128 dimensions)

Cursor will use the MCP server to execute this operation:

I'll create a new collection called 'articles' with the specified fields.

Collection 'articles' has been created successfully with the following schema:
- title: string
- content: string
- vector: float vector[128]

Troubleshooting

Common Issues

Connection Errors

If you see errors like "Failed to connect to Milvus server":

1. Verify your Milvus instance is running: `docker ps` (if using Docker)

2. Check the URI is correct in your configuration

3. Ensure there are no firewall rules blocking the connection

4. Try using `127.0.0.1` instead of `localhost` in the URI

Authentication Issues

If you see authentication errors:

1. Verify your `MILVUS_TOKEN` is correct

2. Check if your Milvus instance requires authentication

3. Ensure you have the correct permissions for the operations you're trying to perform

Tool Not Found

If the MCP tools don't appear in Claude Desktop or Cursor:

1. Restart the application

2. Check the server logs for any errors

3. Verify the MCP server is running correctly

4. Press the refresh button in the MCP settings (for Cursor)

Getting Help

If you continue to experience issues:

1. Check the GitHub Issues for similar problems

2. Join the Milvus Community Discord for support

3. File a new issue with detailed information about your problem