TencentCloud MCP Servers
A suite of specialized MCP servers that help you get the most out of TencentCloud. Build cloud-native applications, manage infrastructure, and accelerate AI development and deployment wherever you use MCP.
🌍 Languages: English | 中文
Table of Contents
- TencentCloud MCP Servers
What is the Model Context Protocol (MCP) and how does it work with TencentCloud MCP Servers?
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.
An MCP Server is a lightweight program that exposes specific capabilities through the standardized Model Context Protocol. Host applications (such as chatbots, IDEs, and other AI tools) have MCP clients that maintain 1:1 connections with MCP servers. Common MCP clients include agentic AI coding assistants (like CodeBuddy, Cursor, Q Developer, Cline, Windsurf) as well as chatbot applications like Claude Desktop, with more clients coming soon. MCP servers can access local data sources and remote services to provide additional context that improves the generated outputs from the models.
TencentCloud MCP Servers use this protocol to provide AI applications access to TencentCloud documentation, contextual guidance, and best practices. Through the standardized MCP client-server architecture, TencentCloud capabilities become an intelligent extension of your development environment or AI application.
TencentCloud MCP servers enable enhanced cloud-native development, infrastructure management, and development workflows—making AI-assisted cloud computing more accessible and efficient.
The Model Context Protocol is an open source project run by Anthropic, PBC. and open to contributions from the entire community. For more information on MCP, you can find further documentation here
Why TencentCloud MCP Servers?
MCP servers enhance the capabilities of foundation models (FMs) in several key ways:
-
Improved Output Quality: By providing relevant information directly in the model's context, MCP servers significantly improve model responses for specialized domains like TencentCloud services. This approach reduces hallucinations, provides more accurate technical details, enables more precise code generation, and ensures recommendations align with current TencentCloud best practices and service capabilities.
-
Workflow Automation: MCP servers convert common workflows into tools that foundation models can use directly.
-
Specialized Domain Knowledge: MCP servers provide deep, contextual knowledge about TencentCloud services that might not be fully represented in foundation models' training data, enabling more accurate and helpful responses for cloud development tasks.
Available MCP Servers: Quick Installation
MCP Server List Sync With TencentCloud Developer MCP Market.
Get started quickly with one-click installation buttons for popular MCP clients. Click the buttons below to install servers directly in CodeBuddy, Cursor or VS Code:
-
If you are using Cursor for local deployment, click in the list for quick installation.
-
If you are using VS Code for local deployment, click in the list for quick installation.
-
If you are using Hosted Deployment mode, click
in the list for quick installation.
Project Management
Development Efficiency
SaaS
PaaS
IaaS
When to use Local vs Remote MCP Servers?
TencentCloud MCP servers can be run either locally on your development machine or remotely on the cloud. Here's when to use each approach:
Local MCP Servers
- Development & Testing: Perfect for local development, testing, and debugging
- Offline Work: Continue working when internet connectivity is limited
- Data Privacy: Keep sensitive data and credentials on your local machine
- Low Latency: Minimal network overhead for faster response times
- Resource Control: Direct control over server resources and configuration
Remote MCP Servers
- Team Collaboration: Share consistent server configurations across your team
- Always Available: Access your MCP servers from anywhere, any device
- Automatic Updates: Get the latest features and security patches automatically
- Scalability: Easily handle varying workloads without local resource constraints
Remote and Local Installation & Setup
Steps for Using Remote Hosted MCP
-
Cloud Configuration
-
Visit the MCP details page in the Tencent Cloud Developer Community MCP Marketplace, using Tencent Cloud COS MCP Server as an example
-
Click the Connect Server button on the details page

-
Agree to the Tencent Cloud Developer MCP Marketplace Software License and Service Agreement and continue

-
Enter the required parameters and click Connect Server to create an SSE URL
Fill in the required parameters, where
Regionis the location of the hosted service andBucketis the name of the storage bucket for the hosted service. These can be obtained and purchased from Tencent Cloud Object Storage.Obtain or generate your SecretID and SecretKey from API Key Management
Please securely store the generated SSE URL and do not disclose it.

-
-
Cloud Testing
- Select the corresponding tool and click Test
The test results are shown in the image below, indicating that the online configuration was successful

- Select the corresponding tool and click Test
-
IDE Configuration for Hosted Services, using CodeBuddy as an example
- Open the IDE settings and find the manual configuration under CodeBuddy
Add the MCP service configuration using the configuration generated by the cloud hosting service
After modification, it should look like the image below{ "mcpServers": { "cos-mcp": { "type": "sse", "url": "https://mcp-api.tencent-cloud.com/sse/<your-token>" // Replace with your own SSE URL token generated from cloud hosting } } }
- Open the IDE settings and find the manual configuration under CodeBuddy
-
Using Cloud-Hosted MCP Services in the IDE
-
In CodeBuddy, enter Help me check what files are in my object storage to use the COS MCP service
Note: Select Craft mode, as chat mode will not call MCP services

CodeBuddy summarizes the content
-
-
More Information
-
Other cloud-hosted MCP services in the Tencent Cloud Developer Community MCP Marketplace can be used following these same steps.

-
Steps for Local Installation of MCP
MCP servers with go source, you can typically:
- Install go from golang, version >= 1.24.1. Skip this step if already installed.
- Using Domain MCP as an example, enter
cd src/domainin the terminal to navigate to the source directory. - Run
go buildto compile the source code, which will generate the executable file domain_server. - Execute
./domain_serverto start the MCP service. - Copy the configuration information output from Step 4 and configure it in your IDE. Configuration

MCP servers with uvx command, you can typically:
-
Install
uvxfrom Astral -
Add the server to your MCP client configuration
-
Use tencent-cvm as example, add tencent-cvm to your MCP client configuration

Example configuration for TencentCloud MCP:
{ "mcpServers":{ "mcp-server-tapd": { "command": "uvx", "args": [ "mcp-server-tapd" ], "env": { "TAPD_API_USER": "", "TAPD_API_PASSWORD": "", "TAPD_API_BASE_URL": "https://api.tapd.cn", "TAPD_BASE_URL": "https://www.tapd.cn", "BOT_URL": "" } }, "tencent-cvm": { "command": "uvx", "args": [ "mcp-server-cvm" ], "env": { "TENCENTCLOUD_SECRET_ID": "YOUR_SECRET_ID_HERE", "TENCENTCLOUD_SECRET_KEY": "YOUR_SECRET_KEY_HERE", "TENCENTCLOUD_REGION": "YOUR_REGION_HERE" } }, "tencent-tat": { "command": "uvx", "args": [ "mcp-server-tat" ], "env": { "TENCENTCLOUD_SECRET_ID": "YOUR_SECRET_ID_HERE", "TENCENTCLOUD_SECRET_KEY": "YOUR_SECRET_KEY_HERE", "TENCENTCLOUD_REGION": "YOUR_REGION_HERE" } }, "tencent-as": { "command": "uvx", "args": [ "mcp-server-as" ], "env": { "TENCENTCLOUD_SECRET_ID": "YOUR_SECRET_ID_HERE", "TENCENTCLOUD_SECRET_KEY": "YOUR_SECRET_KEY_HERE", "TENCENTCLOUD_REGION": "YOUR_REGION_HERE" } } } }
MCP servers with npx command, you can typically:
-
Install
npmfrom Node.js -
Add the server to your MCP client configuration
-
Use cos-mcp as example, add cos-mcp to your MCP client configuration

Example configuration for TencentCloud MCP:
{ "mcpServers": { "edgeone-pages-mcp-server": { "command": "npx", "args": [ "edgeone-pages-mcp" ], "env": { "EDGEONE_PAGES_API_TOKEN": "", "EDGEONE_PAGES_PROJECT_NAME": "" } }, "cos-mcp": { "command": "npx", "args": [ "cos-mcp" ] }, "cloudbase": { "command": "npx", "args": [ "npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest" ], "env": { "INTEGRATION_IDE": "TencentMCPMarket" } }, "tca-mcp-server": { "command": "npx", "args": [ "-y", "-p", "tca-mcp-server@latest", "tca-mcp-stdio" ], "env": { "TCA_TOKEN": "<TCA_TOKEN>", "TCA_USER_NAME": "<TCA_USER_NAME>" } }, "cnb": { "command": "npx", "args": [ "-y", "-p", "@cnbcool/mcp-server", "cnb-mcp-stdio" ], "env": { "API_BASE_URL": "<BASE_URL>", "API_TOKEN": "<YOUR_TOKEN>" } }, "coding-devops": { "command": "npx", "args": [ "-y", "coding-devops-mcp-server" ], "env": { "CODING_TOKEN": "xxxxxxxxxxxxxx" }, "disabled": false, "autoApprove": [] }, } }
Installation and Setup
Getting Started with CodeBuddy
-
Follow the steps above in the Installation and Setup section to install
uvfrom Astral. -
Follow the steps above in the Installation and Setup section to install
npmfrom Node.js. -
You can place MCP configuration in two locations, depending on your use case:
Configure MCP servers in CodeBuddy settings or in ~/Library/Application Support/CodeBuddy/User/globalStorage/tencent.planning-genie/settings/codebuddy_mcp_settings.json.
codebuddy_mcp_settings.json
{
"mcpServers": {
"cloudbase": {
"command": "npx",
"args": ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"]
}
}
}
Getting Started with Cursor
-
Follow the steps above in the Installation and Setup section to install
uvfrom Astral. -
Follow the steps above in the Installation and Setup section to install
npmfrom Node.js. -
You can place MCP configuration in two locations, depending on your use case:
A. Project Configuration
- For tools specific to a project, create a .cursor/mcp.json file in your project directory.
- This allows you to define MCP servers that are only available within that specific project.
B. Global Configuration
- For tools that you want to use across all projects, create a ~/.cursor/mcp.json file in your home directory.
- This makes MCP servers available in all your Cursor workspaces.
.cursor/mcp.json
{
"mcpServers": {
"cloudbase": {
"command": "npx",
"args": ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"]
}
}
}
-
Using MCP in Chat The Composer Agent will automatically use any MCP tools that are listed under Available Tools on the MCP settings page if it determines them to be relevant. To prompt tool usage intentionally, please prompt Cursor to use the desired TencentCloud MCP Server you wish to use. For example,
Using the COS MCP Server, do... -
Tool Approval By default, when Agent wants to use an MCP tool, it will display a message asking for your approval. You can use the arrow next to the tool name to expand the message and see what arguments the Agent is calling the tool with.
Getting Started with Windsurf
-
Follow the steps above in the Installation and Setup section to install
uvfrom Astral, install Python. -
Follow the steps above in the Installation and Setup section to install
npmfrom Node.js -
Access MCP Settings
- Navigate to Windsurf - Settings > Advanced Settings or use the Command Palette > Open Windsurf Settings Page
- Look for the "Model Context Protocol (MCP) Servers" section
-
Add MCP Servers
- Click "Add Server" to add a new MCP server
- You can choose from available templates like GitHub, Puppeteer, PostgreSQL, etc.
- Alternatively, click "Add custom server" to configure your own server
-
Manual Configuration
- You can also manually edit the MCP configuration file located at
~/.codeium/windsurf/mcp_config.json
- You can also manually edit the MCP configuration file located at
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"cloudbase": {
"command": "npx",
"args": ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"]
}
}
}
Getting Started with VS Code
- Follow the steps above in the Installation and Setup section to install
uvfrom Astral, install Python. - Follow the steps above in the Installation and Setup section to install
npmfrom Node.js
Configure MCP servers in VS Code settings or in .vscode/mcp.json (see VS Code MCP docs for more info.):
.vscode/mcp.json
{
"mcpServers": {
"cloudbase": {
"command": "npx",
"args": ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"]
}
}
}
More Information
-
Scan QrCode join the WeChat Group of MCP

Please contact us if you have any questions
