Simple MCP Server

MCP server for Milvus vector database with semantic and full-text search capabilities

Local serverstdio

What is the Simple MCP server?

If you already use Simple, the simple mcp server is the piece that lets your assistant work with it directly. MCP server for Milvus vector database with semantic and full-text search capabilities.

What the server does

This simplified MCP server was created for specific use cases where the official server may not be the best fit:

  • Multiple MCP servers can use the same Milvus database instance with segregated storage
  • Each server instance can operate on different collections (e.g., per-user, per-account, per-application)
  • Enables cost-effective shared infrastructure while maintaining data isolation
  • Perfect for SaaS applications where each customer needs their own vector space
  • Agents and LLMs can struggle with too many tool options, leading to poor decision-making
  • This server provides just 3 focused tools (store_memory, search_memory, forget_memory)

Installation

Installation goes through your MCP client rather than a global install: point it at simple-milvus-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

Configuration is passed through the environment: GEMINI_API_KEY, OPENAI_API_KEY, VERTEX_PROJECT_ID, VERTEX_LOCATION, VERTEX_CREDENTIALS. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Milvus Server: Running Milvus 2.5+ instance - API Keys: Required environment variables for embedding models:

Where it fits

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by blevinstein; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the Simple MCP server

{
  "mcpServers": {
    "milvus-1": {
      "command": "npx",
      "args": ["-y", "simple-milvus-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "VERTEX_PROJECT_ID": "your-value",
        "VERTEX_LOCATION": "your-value",
        "VERTEX_CREDENTIALS": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Milvus Server: Running Milvus 2.5+ instance - API Keys: Required environment variables for embedding models:
VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
VERTEX_PROJECT_IDConfiguration value read at startup.Optional
VERTEX_LOCATIONConfiguration value read at startup.Optional
VERTEX_CREDENTIALSConfiguration value read at startup.Optional

Frequently asked questions

It connects Simple to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Simple directly.