Which integrations are available for this server?

Provides tools for querying and filtering Kubernetes Pod logs from Aliyun Container Service (ACK) clusters, enabling analysis of container logs by namespace and pod name. Enables natural language and SQL-based querying of NGINX logs collected in Aliyun Log Service (SLS) to analyze traffic, request patterns, and error codes.

How do I use aliyun-sls-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@aliyun-sls-mcp Find "timeout" errors in my-project app-logs from the last 15 minutes" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

aliyun-sls-mcp

by SuxyEE

Overview Schema Related Servers Score Discussions

TypeScript

Remote

aliyun-sls-mcp

阿里云 SLS 日志查询 MCP Server —— 让 AI 助手（Cursor / Claude Desktop）直接用自然语言查询阿里云日志服务，告别手动翻控制台。

支持函数计算 FC、SAE 微服务、ECS、ACK 容器、API 网关、RDS 慢查询等所有已接入 SLS 的日志源。多地域并行查询，只读安全，零代码接入，npx 一行启动。

npm version npm downloads License: MIT

GitHub | npm | 阿里云 SLS 文档

这是什么？

你有没有遇到过这种情况：线上出了问题，要去阿里云控制台一页页翻日志，又慢又麻烦？

aliyun-sls-mcp 让你可以在 Cursor 或 Claude Desktop 的对话框里，直接用自然语言查询 SLS 日志：

"查一下 my-project 项目最近 15 分钟的错误日志"
"统计一下最近一小时各接口的报错次数"
"帮我排查今天上午 11 点左右支付服务的 timeout 问题"

AI 会自动调用 SLS API 查出日志，帮你分析问题。

Related MCP server: Alibaba Cloud Observability MCP Server

支持哪些日志来源？

只要你的服务日志写入了阿里云 SLS，就可以用本工具查询。 以下是常见场景：

函数计算 FC（Function Compute）

阿里云函数计算默认将函数执行日志（包括 console.log 输出、错误堆栈、冷启动信息等）持久化到 SLS。

在 FC 控制台 → 函数详情 → 日志，可以看到对应的 SLS Project 和 Logstore，将它们填入对话即可：

查询 fc-log-project aliyun-fc-cn-shenzhen-xxx-log logstore 最近 30 分钟内 my-function 函数的错误日志

注意：FC 日志不包含 __pack_meta__ 字段，无法使用 get_context_logs，可改用 query_logs 按请求 ID 或 __tag__:__pack_id__ 追踪同一次调用的完整日志。

SAE（Serverless 应用引擎）

SAE 支持将应用的标准输出（stdout/stderr）投递到 SLS。开启后可查询所有实例的日志，无需逐台登录。

在 SAE 控制台 → 应用详情 → 日志管理 → 日志采集，配置投递到 SLS 后，即可通过本工具查询：

查询 sae-log-project sae-app-stdout-store 中 my-app 最近 1 小时的日志

ECS / 自建服务

通过阿里云 Logtail 采集器，可以将 ECS 上任意文件日志（如 Nginx 日志、应用日志）采集到 SLS。配置完成后即可查询：

查询 my-nginx-project nginx-access-log 中最近 1 小时状态码为 5xx 的请求

容器服务 ACK（Kubernetes）

ACK 集群可配置将 Pod 日志（容器标准输出）采集到 SLS，支持按 namespace、Pod 名称等字段过滤：

查询 k8s-log-project k8s-stdout 中 namespace 为 production，pod 包含 payment 的最近 15 分钟错误日志

API 网关 / SLB / CDN 访问日志

阿里云 API 网关、SLB 负载均衡、CDN 等产品支持将访问日志自动投递到 SLS，可用于分析流量、排查 4xx/5xx 错误：

统计 apigw-log-project access-log 最近 1 小时各 API 路径的请求量和平均延迟

RDS / 数据库慢查询日志

RDS 审计日志和慢查询日志也可投递到 SLS，配合 SQL 分析功能可快速定位慢查询：

查询 rds-log-project rds-slowquery-log 最近 1 天执行时间超过 1 秒的慢 SQL，按执行次数排序

功能特性

列出项目 — 支持同时查询多个地域，自动发现所有 SLS Project
列出日志库 — 浏览 Project 下的所有 Logstore
查询日志 — 支持时间范围 + SLS 查询语法过滤，适合错误排查
SQL 分析 — 对日志做聚合、统计、分组分析
日志分布图 — 展示某时间段内的日志量分布，快速定位异常时间窗口
上下文日志 — 获取某条日志前后的日志，还原完整执行链路

快速开始

第一步：获取阿里云 AccessKey

AccessKey 是访问阿里云 API 的凭证，类似账号密码，请妥善保管，不要泄露。

打开阿里云 RAM 访问控制台
点击「创建 AccessKey」
记下 AccessKey ID 和 AccessKey Secret（Secret 只显示一次，请立即保存）

最佳实践：建议创建一个子 RAM 用户，只授予 AliyunLogReadOnlyAccess 权限，而不是使用主账号的 AccessKey，这样即使 Key 泄露也不会影响其他服务。

第二步：配置 MCP Server

根据你使用的 AI 工具，找到对应的配置文件并编辑：

Cursor

系统	配置文件路径
Windows	`%USERPROFILE%\.cursor\mcp.json`
macOS / Linux	`~/.cursor/mcp.json`

Claude Desktop

系统	配置文件路径
Windows	`%APPDATA%\Claude\claude_desktop_config.json`
macOS	`~/Library/Application Support/Claude/claude_desktop_config.json`

在配置文件中添加以下内容（如果文件不存在就新建，如果已有内容就在 mcpServers 里追加）：

{
  "mcpServers": {
    "aliyun-sls": {
      "command": "npx",
      "args": ["-y", "aliyun-sls-mcp"],
      "env": {
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "你的AccessKeyId",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "你的AccessKeySecret",
        "SLS_REGIONS": "cn-hangzhou,cn-shenzhen"
      }
    }
  }
}

把以下内容替换成你自己的：

你的AccessKeyId → 第一步获取的 AccessKey ID
你的AccessKeySecret → 第一步获取的 AccessKey Secret
cn-hangzhou,cn-shenzhen → 你的 SLS 数据所在地域，多个用英文逗号分隔，只有一个地域也可以直接填单个，如 cn-shenzhen

地域 ID 怎么查？

登录阿里云 SLS 控制台，进入你的 Project，URL 里会有地域信息，如 cn-shenzhen。也可以参考本文末尾的支持地域列表。

第三步：重启 AI 客户端

保存配置文件后，完全退出并重新打开 Cursor 或 Claude Desktop。

重启后，在对话框输入以下内容验证是否配置成功：

帮我列出所有 SLS 项目

如果返回了你的项目列表，说明配置成功！

环境变量说明

变量名	是否必填	说明
`ALIBABA_CLOUD_ACCESS_KEY_ID`	✅ 必填	阿里云 AccessKey ID
`ALIBABA_CLOUD_ACCESS_KEY_SECRET`	✅ 必填	阿里云 AccessKey Secret
`SLS_REGIONS`	可选	地域配置，多个用英文逗号分隔，单个直接填写即可。如 `cn-hangzhou` 或 `cn-hangzhou,cn-shenzhen,cn-beijing`。不填默认使用 `cn-hangzhou`
`SLS_NETWORK`	可选	网络类型：`public`（默认，公网）或 `vpc`（VPC 内网，适合服务器部署）

对话使用示例

配置成功后，你可以用自然语言告诉 AI 你想做什么，AI 会自动调用合适的工具：

发现资源

列出所有 SLS 项目（会查询所有配置的地域）

列出深圳地域的 SLS 项目

列出 my-project 项目下所有的日志库

查询日志

查询 my-project 项目 app-logs 日志库最近 15 分钟的错误日志

查找 order-service 最近 1 小时内包含 "timeout" 的日志

查询 cn-shanghai 地域 payment-project 项目 order-logs 中最近 30 分钟的日志

统计分析

统计 my-project 最近 1 小时各接口的报错次数，按数量排序

查看 my-project app-logs 最近 1 小时的日志量分布，找出流量高峰时间点

统计今天各函数的调用量和平均耗时

问题排查

帮我排查 2026-03-19 11:00 到 11:30 之间 payment 函数出现的 SLOW SQL 问题

查一下刚才那条报错日志的前后 20 条日志，看看完整的执行链路

可用工具详情

`list_projects` — 列出项目

列出一个或多个地域下的所有 SLS Project。

参数	类型	必填	说明
`regions`	string 或 string[]	否	地域 ID，支持单个字符串或数组。不填则查询 `SLS_REGIONS` / `SLS_REGION` 配置的所有地域

`list_logstores` — 列出日志库

列出某个 Project 下的所有 Logstore。

参数	类型	必填	说明
`project`	string	✅	SLS Project 名称
`region`	string	否	地域 ID，不填则使用默认地域

`query_logs` — 查询日志

按时间范围和过滤条件查询日志，适合错误排查、接口追踪等场景。

参数	类型	必填	默认值	说明
`project`	string	✅	—	SLS Project 名称
`logstore`	string	✅	—	Logstore 名称
`query`	string	否	`*`	SLS 查询语句（见下方示例）
`time_range`	string	否	`15m`	相对时间范围，如 `15m`、`1h`、`1d`
`from`	number	否	—	开始时间（Unix 时间戳，秒），与 `to` 同时使用，优先级高于 `time_range`
`to`	number	否	—	结束时间（Unix 时间戳，秒）
`max_logs`	number	否	`50`	最多返回条数（1-500）
`region`	string	否	—	地域 ID

时间范围格式： 1m 5m 15m 30m 1h 2h 6h 12h 1d 3d 7d

SLS 查询语法示例：

*                              # 所有日志
level: ERROR                   # 错误级别日志
content: timeout               # 包含 timeout 的日志
level: ERROR AND status: 500   # 组合条件（AND 连接）
level: ERROR OR level: WARN    # 任一条件（OR 连接）
NOT level: INFO                # 排除 INFO 日志
requestId: "abc-123-xyz"       # 按请求 ID 追踪

`query_logs_sql` — SQL 分析

对日志执行 SQL 查询，支持聚合、统计、分组，适合趋势分析和问题统计。

参数	类型	必填	默认值	说明
`project`	string	✅	—	SLS Project 名称
`query`	string	✅	—	SQL 语句，FROM 子句填写 Logstore 名称
`time_range`	string	否	`1h`	时间范围
`from`	number	否	—	开始时间（Unix 秒）
`to`	number	否	—	结束时间（Unix 秒）
`region`	string	否	—	地域 ID

SQL 示例：

-- 统计各函数调用量，按数量降序
SELECT functionName, count(*) as total
FROM my-logstore
GROUP BY functionName
ORDER BY total DESC

-- 统计各状态码数量
SELECT statusCode, count(*) as cnt
FROM my-logstore
WHERE statusCode != ''
GROUP BY statusCode
ORDER BY cnt DESC

-- 统计最近 1 小时每分钟的日志量趋势
SELECT date_trunc('minute', __time__) as t, count(*) as cnt
FROM my-logstore
GROUP BY t
ORDER BY t

`get_log_histogram` — 日志分布图

获取某段时间内日志量的分布，用于快速定位流量异常或错误高峰时间点。

参数	类型	必填	默认值	说明
`project`	string	✅	—	SLS Project 名称
`logstore`	string	✅	—	Logstore 名称
`query`	string	否	`*`	过滤条件
`time_range`	string	否	`1h`	时间范围
`from`	number	否	—	开始时间（Unix 秒）
`to`	number	否	—	结束时间（Unix 秒）
`region`	string	否	—	地域 ID

输出示例：

2026/3/19 11:03:00  ███████████████████░░░░░░░░░░░  1996
2026/3/19 11:04:00  ███████████████████████░░░░░░░  2379  ← 流量高峰
2026/3/19 11:05:00  ████████████████░░░░░░░░░░░░░░  1670

`get_context_logs` — 上下文日志

获取某条日志前后的若干条日志，还原事件发生前后的完整执行链路。

注意：此工具需要日志包含 __tag__:__pack_meta__ 字段。阿里云函数计算（FC）的日志通常没有该字段，可以改用 query_logs 按 __tag__:__pack_id__ 过滤同一批次的日志来达到类似效果。

参数	类型	必填	默认值	说明
`project`	string	✅	—	SLS Project 名称
`logstore`	string	✅	—	Logstore 名称
`pack_id`	string	✅	—	目标日志的 `__tag__:__pack_id__` 字段值
`pack_meta`	string	✅	—	目标日志的 `__tag__:__pack_meta__` 字段值
`back_lines`	number	否	`10`	向前获取的条数（最大 100）
`forward_lines`	number	否	`10`	向后获取的条数（最大 100）
`region`	string	否	—	地域 ID

常见问题

Q：配置后 AI 说连不上 / 工具调用失败？

检查 AccessKey ID 和 Secret 是否填写正确，注意不要有多余空格
检查地域 ID 是否正确（如深圳是 cn-shenzhen，不是 shenzhen）
确认 RAM 用户已授予 AliyunLogReadOnlyAccess 权限
确保 Node.js >= 18 已安装（命令行执行 node -v 检查）
完全重启 Cursor 或 Claude Desktop

Q：提示 "No SLS projects found" 但我确实有项目？

可能是地域填错了。登录 SLS 控制台确认你的 Project 所在地域，然后告诉 AI：

查询 cn-shenzhen 地域的 SLS 项目

Q：SLS_REGIONS 只能填一个地域吗？

不是，SLS_REGIONS 同时支持单个或多个地域：

# 单个地域
SLS_REGIONS=cn-shenzhen

# 多个地域（英文逗号分隔）
SLS_REGIONS=cn-shenzhen,cn-hangzhou,cn-beijing

不填时默认使用 cn-hangzhou。

Q：查不到 FC 函数计算的上下文日志？

FC 日志不包含 __pack_meta__ 字段，无法使用 get_context_logs。可以这样替代：

查询 my-project fc-logs 中 __tag__:__pack_id__ 为 "xxx" 的所有日志

本地开发 / 源码运行

适合希望二次开发的用户。

git clone https://github.com/SuxyEE/aliyun-sls-mcp.git
cd aliyun-sls-mcp
npm install
npm run build

配置 MCP 时使用本地路径：

{
  "mcpServers": {
    "aliyun-sls": {
      "command": "node",
      "args": ["e:\\tools\\aliyun-sls-mcp\\dist\\index.js"],
      "env": {
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "你的AccessKeyId",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "你的AccessKeySecret",
        "SLS_REGIONS": "cn-hangzhou"
      }
    }
  }
}

开发命令：

npm run dev    # 监听文件变化，自动重新编译
npm run build  # 构建一次
npm start      # 运行（用于验证启动是否正常）

支持的地域

亚太

地域名称	地域 ID
华北1（青岛）	`cn-qingdao`
华北2（北京）	`cn-beijing`
华北3（张家口）	`cn-zhangjiakou`
华北5（呼和浩特）	`cn-huhehaote`
华北6（乌兰察布）	`cn-wulanchabu`
华东1（杭州）	`cn-hangzhou`
华东2（上海）	`cn-shanghai`
华东5（南京-本地地域）	`cn-nanjing`
华东6（福州-本地地域）	`cn-fuzhou`
华南1（深圳）	`cn-shenzhen`
华南2（河源）	`cn-heyuan`
华南3（广州）	`cn-guangzhou`
西南1（成都）	`cn-chengdu`
中国香港	`cn-hongkong`
日本（东京）	`ap-northeast-1`
韩国（首尔）	`ap-northeast-2`
新加坡	`ap-southeast-1`
马来西亚（吉隆坡）	`ap-southeast-3`
印度尼西亚（雅加达）	`ap-southeast-5`
菲律宾（马尼拉）	`ap-southeast-6`
泰国（曼谷）	`ap-southeast-7`

欧洲与美洲

地域名称	地域 ID
美国（硅谷）	`us-west-1`
美国（弗吉尼亚）	`us-east-1`
美国（亚特兰大）	`us-southeast-1`
德国（法兰克福）	`eu-central-1`
英国（伦敦）	`eu-west-1`

中东

地域名称	地域 ID
沙特（利雅得）	`me-central-1`
阿联酋（迪拜）	`me-east-1`

行业云

地域名称	地域 ID
华北2 金融云	`cn-beijing-finance-1`
华东1 金融云	`cn-hangzhou-finance`
华东2 金融云	`cn-shanghai-finance-1`
华南1 金融云	`cn-shenzhen-finance-1`
河源专属云（汽车合规）	`cn-heyuan-acdr-1`

完整接入点列表参见阿里云 SLS 服务接入点文档。

技术栈

语言：TypeScript
运行时：Node.js >= 18
MCP SDK：@modelcontextprotocol/sdk
SLS SDK：@alicloud/sls20201230

License

MIT

Available Tools

6 tools

get_context_logsA

Retrieve log lines before and after a specific log entry using its pack_id and pack_meta. First query logs with query_logs to find a log entry, then use its tag:pack_id and tag:pack_meta fields to get surrounding context. Useful for understanding full execution flow around an error.

ParametersJSON Schema

Name	Required	Description
`project`	Yes	SLS project name
`logstore`	Yes	SLS logstore name
`pack_id`	Yes	The pack_id of the target log entry. Found in the __tag__:__pack_id__ field of any log. Example: "7FDBA9CB41D1D6F93C49A936ADF9C8FC-1B54"
`pack_meta`	Yes	The pack_meta (unique context identifier) of the target log entry within the log group. Found in the __tag__:__pack_meta__ field. Example: "0\|MTY1NTcwNTUzODY5MTY0MDk1Mg==\|3\|0"
`back_lines`	No	Number of log lines before the target log (default: 10, max: 100)
`forward_lines`	No	Number of log lines after the target log (default: 10, max: 100)
`region`	No	Alibaba Cloud region ID, e.g. cn-hangzhou. Defaults to SLS_REGION env variable.

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explains the tool's purpose and workflow but lacks details on permissions, rate limits, error handling, or response format. The description doesn't contradict annotations, but it doesn't fully compensate for the absence of structured behavioral hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured in two sentences. The first sentence states the purpose, and the second provides usage guidelines and context. Every sentence adds value with no wasted words, and it's front-loaded with the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, no annotations, no output schema), the description is adequate but incomplete. It explains the purpose and workflow but lacks details on output format, error cases, or behavioral constraints. Without annotations or output schema, more context would be helpful for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by mentioning pack_id and pack_meta fields but doesn't provide additional syntax or format details. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Retrieve log lines before and after a specific log entry using its pack_id and pack_meta.' It specifies the verb ('retrieve'), resource ('log lines'), and scope ('before and after a specific log entry'), and distinguishes it from sibling tools by mentioning query_logs as a prerequisite step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'First query logs with query_logs to find a log entry, then use its __tag__:__pack_id__ and __tag__:__pack_meta__ fields to get surrounding context.' It names the alternative tool (query_logs) and specifies when to use this tool (after finding a log entry) versus when not to (for initial log queries).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_log_histogramA

Get the time-series distribution of log counts matching a query. Returns a visual histogram showing log volume over time. Useful for identifying when errors spiked or when unusual activity occurred.

ParametersJSON Schema

Name	Required	Description	Default
`project`	Yes	SLS project name
`logstore`	Yes	SLS logstore name
`query`	No	SLS query statement to filter logs. Default: "*" for all logs	*
`time_range`	No	Relative time range. Formats: 15m, 1h, 6h, 12h, 1d, 3d	1h
`from`	No	Start time as Unix timestamp (seconds). Overrides time_range.
`to`	No	End time as Unix timestamp (seconds).
`region`	No	Alibaba Cloud region ID, e.g. cn-hangzhou. Defaults to SLS_REGION env variable.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return format ('Returns a visual histogram showing log volume over time') and practical use case, but doesn't cover aspects like rate limits, authentication needs, error handling, or whether this is a read-only operation (though 'Get' implies it).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured in three sentences: the core function, the return format, and the use case. Every sentence adds value without redundancy, making it appropriately sized and front-loaded with essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters, no annotations, and no output schema, the description provides adequate context on purpose and usage but lacks details on behavioral aspects like permissions, rate limits, or error responses. It's complete enough for basic understanding but has gaps given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 7 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline of 3 when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('Get the time-series distribution of log counts matching a query') and resource ('log counts'), distinguishing it from siblings like get_context_logs or query_logs by focusing on histogram/visual distribution rather than raw log retrieval or SQL queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('Useful for identifying when errors spiked or when unusual activity occurred'), but it doesn't explicitly state when not to use it or name alternatives among the sibling tools, which would be needed for a score of 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_logstoresA

List all logstores within an SLS project. Use this to discover available logstores before querying logs.

ParametersJSON Schema

Name	Required	Description	Default
`project`	Yes	SLS project name
`region`	No	Alibaba Cloud region ID where the project resides, e.g. cn-hangzhou, cn-shenzhen. Defaults to SLS_REGION env variable.

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool lists logstores but doesn't cover critical aspects like whether it's a read-only operation, potential rate limits, authentication needs, or what the output format looks like. This leaves significant gaps for an agent to understand the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with zero waste—each sentence directly contributes to understanding the tool's purpose and usage. It's front-loaded with the core action and efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (simple list operation) and high schema coverage, the description is somewhat complete but lacks output details (no output schema) and behavioral context. It covers the basics but doesn't fully compensate for the absence of annotations, leaving room for improvement in transparency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents both parameters ('project' and 'region') adequately. The description adds no additional parameter semantics beyond what the schema provides, which meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('all logstores within an SLS project'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'list_projects' beyond the resource scope, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for usage ('to discover available logstores before querying logs'), which implicitly suggests when to use this tool. It doesn't explicitly state when not to use it or name alternatives, but the guidance is helpful and contextually relevant.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_projectsA

List all SLS projects in one or more Alibaba Cloud regions. Pass a single region string or an array of region IDs. If omitted, queries all regions configured in SLS_REGIONS / SLS_REGION env variables. Use this to discover available projects before querying logs.

ParametersJSON Schema

Name	Required	Description	Default
`regions`	No	One or more Alibaba Cloud region IDs to query. Accepts a single string (e.g. "cn-hangzhou") or an array (e.g. ["cn-hangzhou","cn-shenzhen"]). Defaults to all regions configured in SLS_REGIONS / SLS_REGION env variables.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden and does well by explaining the default behavior (uses env variables when regions omitted) and the tool's purpose in the workflow. However, it doesn't mention potential rate limits, authentication needs, or pagination behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tightly focused sentences with zero waste: first states core functionality, second explains parameter usage, third provides usage context. Every sentence earns its place by adding distinct value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter read operation with no annotations and no output schema, the description provides good context about the tool's role in the workflow and default behavior. However, without output schema, it doesn't describe what the returned project list looks like.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents the single parameter. The description adds minimal value beyond the schema by mentioning the parameter can be omitted, which is already implied by the schema's optional nature.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('SLS projects'), specifies the scope ('in one or more Alibaba Cloud regions'), and distinguishes from siblings by mentioning its discovery purpose before querying logs (unlike sibling tools that directly query logs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use this tool ('to discover available projects before querying logs'), provides an alternative scenario (if regions omitted, uses env variables), and distinguishes from sibling tools by positioning it as a prerequisite step for log querying operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

query_logsA

Query log data from an SLS logstore with a time range and optional filter query. Returns formatted log entries. Use for debugging, error investigation, and log analysis. Supports SLS query syntax like "level: ERROR", "content: timeout", "status: 500 AND method: POST".

ParametersJSON Schema

Name	Required	Description	Default
`project`	Yes	SLS project name
`logstore`	Yes	SLS logstore name
`query`	No	SLS query statement. Examples: "*" for all logs, "level: ERROR", "content: timeout", "level: ERROR AND status: 500"	*
`time_range`	No	Relative time range. Formats: 1m, 5m, 15m, 30m, 1h, 2h, 6h, 12h, 1d, 3d, 7d	15m
`from`	No	Start time as Unix timestamp (seconds). Overrides time_range if provided.
`to`	No	End time as Unix timestamp (seconds). Used with from parameter.
`max_logs`	No	Maximum number of logs to return (1-500). Default: 50
`region`	No	Alibaba Cloud region ID, e.g. cn-hangzhou. Defaults to SLS_REGION env variable.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the core functionality (querying logs with time range and filters) and mentions the return format ('formatted log entries'), but lacks details about authentication requirements, rate limits, pagination behavior, error handling, or whether this is a read-only operation (though implied by 'query').

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured in two sentences: the first states the core functionality, the second provides usage context and syntax examples. Every element serves a purpose with zero wasted words, making it easy to parse while remaining comprehensive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 8 parameters and no output schema, the description provides adequate context about what the tool does and when to use it, but lacks details about the return format (beyond 'formatted log entries'), error conditions, authentication requirements, and behavioral constraints. With no annotations and no output schema, more completeness would be beneficial for this query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description adds minimal value beyond the schema by mentioning 'time range and optional filter query' and providing SLS syntax examples, but doesn't explain parameter interactions (e.g., time_range vs from/to override) or add significant semantic context not already in the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verb ('query'), resource ('log data from an SLS logstore'), and scope ('with a time range and optional filter query'). It distinguishes itself from siblings by specifying it returns formatted log entries for debugging/analysis, unlike get_log_histogram (statistical) or query_logs_sql (SQL-based).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool ('for debugging, error investigation, and log analysis') and mentions SLS query syntax, which helps differentiate it from SQL-based alternatives. However, it doesn't explicitly state when NOT to use it or provide direct comparisons with specific sibling tools like get_context_logs or query_logs_sql.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

query_logs_sqlA

Execute a SQL query against an SLS project for log analysis and aggregation. Best for counting, grouping, statistical analysis. Example: "SELECT status, count(*) as cnt FROM WHERE time > 1700000000 GROUP BY status".

ParametersJSON Schema

Name	Required	Description	Default
`project`	Yes	SLS project name
`query`	Yes	SQL query with mandatory time range. Must include FROM clause with logstore and time filter using __date__ or __time__. Example: "SELECT status, count(*) as cnt FROM <logstore> WHERE __date__ > '2024-01-01 00:00:00' GROUP BY status ORDER BY cnt DESC"
`time_range`	No	Relative time range used to fill __time__ filter. Formats: 15m, 1h, 6h, 1d	1h
`from`	No	Start time as Unix timestamp (seconds). Overrides time_range.
`to`	No	End time as Unix timestamp (seconds).
`region`	No	Alibaba Cloud region ID, e.g. cn-hangzhou. Defaults to SLS_REGION env variable.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool's analytical purpose and provides an example query, but doesn't cover important behavioral aspects like authentication requirements, rate limits, error handling, or what happens when queries fail. The description adds some value but leaves significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly sized with two sentences: the first states purpose and optimal use case, the second provides a concrete example. Every element earns its place, and the information is front-loaded with the core functionality stated immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex SQL execution tool with 6 parameters and no output schema, the description provides adequate purpose and usage context but lacks important behavioral details. Without annotations covering safety, authentication, or limits, and without an output schema, the description should do more to prepare the agent for proper tool invocation and result interpretation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. It mentions SQL queries generally but doesn't provide additional parameter semantics, earning the baseline score for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Execute a SQL query'), target resource ('against an SLS project'), and purpose ('for log analysis and aggregation'). It distinguishes from sibling tools like 'get_context_logs' or 'get_log_histogram' by specifying SQL-based analysis capabilities. The example further clarifies the scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about when to use this tool ('Best for counting, grouping, statistical analysis'), but doesn't explicitly mention when NOT to use it or name specific alternatives among the sibling tools. It implies usage for complex analytical queries versus simpler retrieval operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

6 tool updatesv0.1.3Mar 19, 2026
- First observedget_context_logs
- First observedget_log_histogram
- First observedlist_logstores
- First observedlist_projects
- First observedquery_logs
- First observedquery_logs_sql

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: list_projects and list_logstores are for discovery, query_logs and query_logs_sql are for different query methods, get_log_histogram provides time-series analysis, and get_context_logs offers contextual retrieval. The descriptions explicitly differentiate their use cases, eliminating any ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (e.g., list_projects, query_logs, get_log_histogram). The naming is predictable and readable throughout, making it easy for agents to understand the action and target resource without confusion.

Tool Count5/5

With 6 tools, the server is well-scoped for log analysis and management in Aliyun SLS. Each tool earns its place by covering essential operations like discovery, querying, aggregation, and contextual analysis, without being overly sparse or bloated for the domain.

Completeness4/5

The toolset provides strong coverage for core log analysis workflows, including discovery, querying, aggregation, and contextual retrieval. A minor gap exists in lacking explicit CRUD operations for managing logstores or projects (e.g., create/delete), but this is reasonable for a read-focused analysis server, and agents can still perform most tasks effectively.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Polar SignalsOAuth
com.polarsignals.api
The Polar Signals MCP server enables AI assistants to connect directly with performance profiling data, allowing users to analyze application performance through natural language queries. Key capabilities include querying CPU performance and memory usage, exploring profiling metadata like profile types and labels, and providing AI-driven code optimization suggestions directly within development environments like Claude Code or Cursor.
Monitoring Developer Tools Observability
2
Foam Observability
io.github.foam-ai
Query application logs, traces, and metrics from your AI coding assistant via Foam's MCP server.
Observability Monitoring Developer Tools
2
Dot - AI Data AnalystOAuth
io.github.zurferr
Ask data questions in natural language. Get SQL, insights, and charts from your databases.
Search Databases Data Visualization
2
CloudQuellOAuth
com.cloudquell
Connects AI assistants to CloudQuell multi-cloud and AI cost, savings, anomaly, and budget data.
Cloud Platforms Monitoring Finance
1

Related MCP Servers

Aliyun MCP Server
Cloud Platforms Search RAG Systems
nailuoGG
F
license
B
quality
C
maintenance
A Claude integration tool that enables users to query and analyze Aliyun (Alibaba Cloud) Simple Log Service logs through natural language commands.
Updated a year ago (2025-03-26 06:13 UTC)
1
26
2
-
Alibaba Cloud Observabilityofficial
Observability Cloud Platforms
aliyun
F
license
A
quality
B
maintenance
Provides tools for accessing Alibaba Cloud observability products including SLS (Log Service) and ARMS (Application Real-time Monitoring Service), allowing any MCP-compatible AI assistants to quickly interact with these services.
Updated a month ago (2026-08-12 03:12 UTC)
9
164
-
CLS MCP Server
Observability Monitoring Cloud Platforms
Tinker-LGD2026
A
license
A
quality
D
maintenance
Provides a suite of 33 tools for interacting with Tencent Cloud Log Service (CLS), enabling log analysis, PromQL metrics queries, and resource management. It allows AI assistants to perform CQL/SQL retrieval, manage alarm strategies, and handle data processing tasks with tiered permission controls.
Updated 5 months ago (2026-04-02 12:53 UTC)
24
6
Apache 2.0
Alibaba Cloud MCP Server
Cloud Platforms Developer Tools
ahmedselimmansor-ctrl
F
license
C
quality
D
maintenance
Enables AI assistants to manage Alibaba Cloud resources via natural language, with explicit tools for common services and a universal API invoker for full cloud coverage.
Updated 4 months ago (2026-05-16 02:00 UTC)
9
2
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SuxyEE/aliyun-sls-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

aliyun-sls-mcp

这是什么？

支持哪些日志来源？

函数计算 FC（Function Compute）

SAE（Serverless 应用引擎）

ECS / 自建服务

容器服务 ACK（Kubernetes）

API 网关 / SLB / CDN 访问日志

RDS / 数据库慢查询日志

功能特性

快速开始

第一步：获取阿里云 AccessKey

第二步：配置 MCP Server

第三步：重启 AI 客户端

环境变量说明

对话使用示例

可用工具详情

list_projects — 列出项目

list_logstores — 列出日志库

query_logs — 查询日志

query_logs_sql — SQL 分析

get_log_histogram — 日志分布图

get_context_logs — 上下文日志

常见问题

本地开发 / 源码运行

支持的地域

亚太

欧洲与美洲

中东

行业云

技术栈

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Alibaba Cloud Observabilityofficial

Latest Blog Posts

MCP directory API

`list_projects` — 列出项目

`list_logstores` — 列出日志库

`query_logs` — 查询日志

`query_logs_sql` — SQL 分析

`get_log_histogram` — 日志分布图

`get_context_logs` — 上下文日志