TOS MCP Server

What does “TOS” MCP Server do?

The TOS MCP Server is an official offering designed to provide powerful querying capabilities for ByteDance Volcengine’s TOS (Tencent Object Storage) platform. It enables users to explore and retrieve stored content using natural language, making data access more intuitive and efficient. By leveraging the Model Context Protocol (MCP), this server allows AI assistants and developer tools to perform seamless database queries, manage files, and interact with storage services programmatically. This enhances developer workflows by simplifying resource discovery and supporting integration with other Volcengine cloud products, enabling more intelligent business applications and automation.

List of Prompts

• 列举火山引擎 TOS 的存储桶列表。
  Prompt template for listing all TOS buckets in an account.
• 列举火山引擎 TOS 的 example 桶下的对象。
  Prompt template for listing objects within a specific TOS bucket.

List of Resources

• 存储桶 (Buckets)
  A resource representing storage containers within TOS, used to organize and manage objects.
• 对象 (Objects)
  Represents individual files or data entries stored inside a bucket, accessible and manageable via the server.
• 存储桶属性 (Bucket Properties)
  Includes metadata such as bucket name, creation time, location, and access domains.
• 对象属性 (Object Properties)
  Includes object name, modification time, ETag, size, and storage type.

List of Tools

• list_buckets
  Retrieves a list of all storage buckets in the user’s Volcengine TOS account, including details like bucket names, creation times, and access domains.
• list_objects
  Lists objects within a specified TOS bucket, with options for filtering by prefix, pagination, and continuation tokens.
• get_object
  Fetches detailed information or content for a specific object stored in a TOS bucket.

Use Cases of this MCP Server

• Storage Resource Exploration
  Developers and AI assistants can quickly enumerate available buckets and objects to understand and audit data inventory.
• Data Retrieval for AI Workflows
  LLMs and automation scripts can fetch files or metadata for analysis, training, or further processing.
• Efficient Content Management
  Allows users to manage large collections of files, supporting operations like listing, filtering, and fetching object details via standardized tools.
• Integration with Intelligent Business Applications
  Combines with other Volcengine MCP products to build data-driven workflows, such as auto-indexing, search, and content recommendation.
• Automated Reporting and Audit
  Regularly lists and checks storage contents to support compliance and monitoring requirements.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Open your Windsurf configuration file.
3. Add the TOS MCP Server to the mcpServers section using the following JSON:

   {
     "mcpServers": {
       "tos-mcp": {
         "command": "npx",
         "args": ["@tos/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the setup by running a test MCP query in Windsurf.

Claude

1. Check that Node.js is installed.
2. Go to your Claude tool’s configuration directory.
3. Insert the TOS MCP Server under mcpServers:

   {
     "mcpServers": {
       "tos-mcp": {
         "command": "npx",
         "args": ["@tos/mcp-server@latest"]
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm connectivity by issuing a sample prompt.

Cursor

1. Make sure Node.js is available.
2. Locate Cursor’s configuration file.
3. Add the TOS MCP Server in the mcpServers array:

   {
     "mcpServers": {
       "tos-mcp": {
         "command": "npx",
         "args": ["@tos/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cursor.
5. Test the setup with a prompt that lists buckets.

Cline

1. Install Node.js if not present.
2. Open the Cline configuration file for MCP servers.
3. Add the TOS MCP Server:

   {
     "mcpServers": {
       "tos-mcp": {
         "command": "npx",
         "args": ["@tos/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Verify by listing TOS resources.

Securing API Keys:
Store sensitive credentials as environment variables. Example:

{
  "mcpServers": {
    "tos-mcp": {
      "command": "npx",
      "args": ["@tos/mcp-server@latest"],
      "env": {
        "TOS_ACCESS_KEY": "YOUR_ACCESS_KEY",
        "TOS_SECRET_KEY": "YOUR_SECRET_KEY"
      },
      "inputs": {
        "region": "ap-guangzhou"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "tos-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “tos-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

This MCP server offers clear documentation and practical tools for interacting with TOS storage resources. It supports a range of use cases, from simple resource listing to integration in intelligent workflows. However, the documentation does not mention support for Roots or Sampling.

Based on the tables above, I would rate this MCP server a 7/10: it has solid functionality and instructions, but lacks clarity on advanced MCP features like Roots and Sampling, and is missing a LICENSE file.

MCP Score