Vikingdb MCP Server

🚀 VikingDB MCP Server

An MCP server implemented for VikingDB storage and search.

What is VikingDB

VikingDB is a high-performance vector database developed by ByteDance.

You can easily use it by referring to the following documentation: https://www.volcengine.com/docs/84313/1254444

Tools

This server implements the following tools:

• vikingdb-collection-intro: Introduces VikingDB's collections.
• vikingdb-index-intro: Introduces VikingDB's indexes.
• vikingdb-upsert-information: Inserts information into VikingDB for later use.
• vikingdb-search-information: Searches for information in VikingDB.

Configuration

• vikingdb_host: The host of the VikingDB server to use.
• vikingdb_region: The region of the VikingDB server to use.
• vikingdb_ak: The access key of the VikingDB server to use.
• vikingdb_sk: The secret key of the VikingDB server to use.
• collection_name: The name of the collection to use.
• index_name: The name of the index to use.

🚀 Quick Start

Installation

Install via Smithery

To automatically install the VikingDB MCP server for Claude Desktop:

npx -y @smithery/cli install mcp-server-vikingdb --client claude

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

Configuration for Development/Unreleased Server

{
  "mcpServers": {
    "mcp-server-vikingdb": {
      "command": "uv",
      "args": [
        "--directory",
        "The directory where mcp-server-vikingdb is located",
        "run",
        "mcp-server-vikingdb",
        "--vikingdb-host", 
        "Your hostname",
        "--vikingdb-region", 
        "Your region",
        "--vikingdb-ak", 
        "Your access key",
        "--vikingdb-sk", 
        "Your secret key",
        "--collection-name",
        "Your collection name",
        "--index-name",
        "Your index name"
      ]
    }
  }
}

Configuration for Released Server

{
    "mcpServers": {
      "mcp-server-vikingdb": {
        "command": "uvx",
        "args": [
          "mcp-server-vikingdb",
          "--vikingdb-host", 
          "Your hostname",
          "--vikingdb-region", 
          "Your region",
          "--vikingdb-ak", 
          "Your access key",
          "--vikingdb-sk", 
          "Your secret key",
          "--collection-name",
          "Your collection name",
          "--index-name",
          "Your index name"
        ]
      }
    }
  } 

🛠️ Development

Build and Publish

To prepare the distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the release:

uv build

This will create source and wheel distributions in the dist/ directory. 3. Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command-line arguments:

• Token: --token or UV_PUBLISH_TOKEN
• Or use username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs via stdio, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector using npm with the following command:

npx @modelcontextprotocol/inspector uv --directory dir_to_mcp_server_vikingdb run mcp-server-vikingdb --vikingdb-host your_host --vikingdb-region your_region --vikingdb-ak your_access_key --vikingdb-sk your_secret_key --collection-name your_collection_name --index-name your_index_name

After starting, the Inspector will display a URL that you can access in your browser to start debugging.