Tencent Cloud Log Service (CLS) MCP Server
Enables large language models to directly access Tencent Cloud Log Service for log search, metric queries, and alarm management without code.
README
Tencent Cloud Log Service (CLS) MCP Server
English | δΈζ
Tencent Cloud Log Service (CLS) MCP Server, built on the Model Context Protocol. It enables large language models to directly access CLS capabilities such as log search, metric queries, and alarm management β no code required.
Features
Log Search
| Tool | Description |
|---|---|
SearchLog |
Search logs based on query conditions (CQL syntax) |
DescribeLogContext |
Retrieve the context (preceding and following N entries) of a specific log |
TextToSearchLogQuery |
Convert natural language descriptions into CLS query statements (CQL expert) |
DescribeLogHistogram |
Get log distribution histogram data within a specified time range |
DescribeIndex |
Get index configuration of a log topic (fields, full-text index, etc.) |
Metric Query
| Tool | Description |
|---|---|
QueryMetric |
Query real-time values of metric topics (PromQL syntax) |
QueryRangeMetric |
Query metric data trends over a time range |
Alarm Management
| Tool | Description |
|---|---|
DescribeAlarms |
List alarm policies with filtering support |
DescribeAlertRecordHistory |
Query alarm trigger/recovery history records |
GetAlarmLog |
Query alarm execution detail logs |
DescribeAlarmNotices |
List notification channel groups (email, SMS, WeChat, etc.) |
DescribeAlarmShields |
List alarm shield rules for a notification channel group |
DescribeNoticeContents |
List notification content templates |
DescribeWebCallbacks |
List webhook callback configurations |
GetAlarmDetail |
Get alarm details by parsing alarm notification URL (supports short/long links) |
Utilities
| Tool | Description |
|---|---|
GetTopicInfoByName |
Search log or metric topics by name |
GetRegionCodeByName |
Get Tencent Cloud region codes by region name |
ConvertTimeStringToTimestamp |
Convert time strings to timestamps |
ConvertTimestampToTimeString |
Convert timestamps to time strings |
Use Cases
- Natural Language Log Query β Search logs using natural language without mastering complex query syntax, significantly reducing the barrier to log analysis.
- Intelligent O&M Troubleshooting β Integrate into O&M workflows to intelligently analyze system anomalies and quickly locate root causes.
- Automated Query Generation β Automatically generate CLS query statements from natural language via
TextToSearchLogQuery, enabling more precise and efficient log retrieval. - Business Metric Monitoring β Query and monitor real-time metric values and historical trends to keep track of system health.
- Alarm Management & Analysis β View alarm policies, query alarm trigger/recovery history, and analyze alarm execution details to quickly understand alerting status.
Configuration
| Parameter | Required | Default | Description |
|---|---|---|---|
TRANSPORT |
No | stdio |
MCP transport mode: stdio, http (Streamable HTTP), or sse |
TENCENTCLOUD_SECRET_ID |
Yes | - | Tencent Cloud API SecretId |
TENCENTCLOUD_SECRET_KEY |
Yes | - | Tencent Cloud API SecretKey |
TENCENTCLOUD_API_BASE_HOST |
No | tencentcloudapi.com |
Tencent Cloud API base host. Use internal.tencentcloudapi.com in VPC intranet environments |
MAX_LENGTH |
No | Unlimited | Max response length, used to fit model token limits |
PORT |
No | 3000 |
Server port for http / sse mode |
TZ |
No | System timezone | Timezone setting, e.g. Asia/Shanghai. Used by time conversion tools (ConvertTimeStringToTimestamp, ConvertTimestampToTimeString) |
Getting Started
Option 1: NPX (Recommended for Local Deployment)
Add the following to your MCP client's mcpServers configuration:
Prerequisites: Install Node.js (LTS version recommended) and obtain Tencent Cloud SecretId and SecretKey.
{
"mcpServers": {
"cls-mcp-server": {
"isActive": true,
"name": "cls-mcp-server",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"cls-mcp-server@latest"
],
"env": {
"TRANSPORT": "stdio",
"TENCENTCLOUD_SECRET_ID": "<YOUR_SECRET_ID>",
"TENCENTCLOUD_SECRET_KEY": "<YOUR_SECRET_KEY>",
"TZ": "Asia/Shanghai"
}
}
}
}
To deploy within a Tencent Cloud VPC, add
"TENCENTCLOUD_API_BASE_HOST": "internal.tencentcloudapi.com"toenv.
Option 2: Self-hosted Streamable HTTP Mode
Prerequisites: Install Node.js (LTS version recommended) and obtain Tencent Cloud SecretId and SecretKey.
This server runs Streamable HTTP in stateless mode β each request is independent, which makes it suitable for containerized deployments and horizontal scaling.
- Create a
.envfile in the current directory:
TRANSPORT=http
TENCENTCLOUD_SECRET_ID=<YOUR_SECRET_ID>
TENCENTCLOUD_SECRET_KEY=<YOUR_SECRET_KEY>
# Uncomment the following line if deploying within a Tencent Cloud VPC
# TENCENTCLOUD_API_BASE_HOST=internal.tencentcloudapi.com
PORT=3000
TZ=Asia/Shanghai
- Start the server:
npx -y cls-mcp-server@latest
- Configure your MCP client:
{
"mcpServers": {
"cls-mcp-server": {
"name": "cls-mcp-server",
"type": "http",
"isActive": true,
"url": "http://localhost:3000/mcp"
}
}
}
Option 3: Self-hosted SSE Mode
Prerequisites: Install Node.js (LTS version recommended) and obtain Tencent Cloud SecretId and SecretKey.
- Create a
.envfile in the current directory:
TRANSPORT=sse
TENCENTCLOUD_SECRET_ID=<YOUR_SECRET_ID>
TENCENTCLOUD_SECRET_KEY=<YOUR_SECRET_KEY>
# Uncomment the following line if deploying within a Tencent Cloud VPC
# TENCENTCLOUD_API_BASE_HOST=internal.tencentcloudapi.com
PORT=3000
TZ=Asia/Shanghai
- Start the server:
npx -y cls-mcp-server@latest
- Configure your MCP client:
{
"mcpServers": {
"cls-mcp-server": {
"name": "cls-mcp-server",
"type": "sse",
"isActive": true,
"baseUrl": "http://localhost:3000/sse"
}
}
}
Option 4: Install from Source
Prerequisites: Install Node.js (LTS version recommended) and obtain Tencent Cloud SecretId and SecretKey.
- Clone the repository and build:
git clone <repository-url>
cd cls-mcp-server
npm install
npm run build
- Stdio Mode β Add the following to your MCP client's
mcpServersconfiguration:
{
"mcpServers": {
"cls-mcp-server": {
"isActive": true,
"name": "cls-mcp-server",
"type": "stdio",
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/cls-mcp-server/dist/index.js"
],
"env": {
"TRANSPORT": "stdio",
"TENCENTCLOUD_SECRET_ID": "<YOUR_SECRET_ID>",
"TENCENTCLOUD_SECRET_KEY": "<YOUR_SECRET_KEY>",
"TZ": "Asia/Shanghai"
}
}
}
}
To deploy within a Tencent Cloud VPC, add
"TENCENTCLOUD_API_BASE_HOST": "internal.tencentcloudapi.com"toenv.
- Streamable HTTP Mode β Create a
.envfile in the project root:
TRANSPORT=http
TENCENTCLOUD_SECRET_ID=<YOUR_SECRET_ID>
TENCENTCLOUD_SECRET_KEY=<YOUR_SECRET_KEY>
# Uncomment the following line if deploying within a Tencent Cloud VPC
# TENCENTCLOUD_API_BASE_HOST=internal.tencentcloudapi.com
PORT=3000
TZ=Asia/Shanghai
Start the server:
npm run start
Then configure your MCP client:
{
"mcpServers": {
"cls-mcp-server": {
"name": "cls-mcp-server",
"type": "http",
"isActive": true,
"url": "http://localhost:3000/mcp"
}
}
}
- SSE Mode β Create a
.envfile in the project root:
TRANSPORT=sse
TENCENTCLOUD_SECRET_ID=<YOUR_SECRET_ID>
TENCENTCLOUD_SECRET_KEY=<YOUR_SECRET_KEY>
# Uncomment the following line if deploying within a Tencent Cloud VPC
# TENCENTCLOUD_API_BASE_HOST=internal.tencentcloudapi.com
PORT=3000
TZ=Asia/Shanghai
Start the server:
npm run start
Then configure your MCP client:
{
"mcpServers": {
"cls-mcp-server": {
"name": "cls-mcp-server",
"type": "sse",
"isActive": true,
"baseUrl": "http://localhost:3000/sse"
}
}
}
Option 5: Docker Deployment
Prerequisites: Install Docker and obtain Tencent Cloud SecretId and SecretKey.
- Build the Docker image:
docker build -t cls-mcp-server .
- Run the container (Streamable HTTP mode, default):
To deploy within a Tencent Cloud VPC, add
-e TENCENTCLOUD_API_BASE_HOST=internal.tencentcloudapi.com.
docker run -d -p 3000:3000 \
-e TENCENTCLOUD_SECRET_ID=<YOUR_SECRET_ID> \
-e TENCENTCLOUD_SECRET_KEY=<YOUR_SECRET_KEY> \
-e TZ=Asia/Shanghai \
--name cls-mcp-server \
cls-mcp-server
To run the SSE transport instead, add
-e TRANSPORT=sseand point the client at/ssewith"type": "sse".
- Configure your MCP client:
{
"mcpServers": {
"cls-mcp-server": {
"name": "cls-mcp-server",
"type": "http",
"isActive": true,
"url": "http://localhost:3000/mcp"
}
}
}
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.