Provides tools for searching Steam games, retrieving user reviews with various filters, and fetching game details such as pricing, tags, and descriptions.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@steam-mcp search for Cyberpunk 2077"
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.
这是一个基于 Model Context Protocol (MCP) 的 Steam 评论获取工具，可以获取 Steam 游戏的用户评论、搜索游戏和获取游戏详情。
游戏搜索: 根据关键词搜索 Steam 游戏
评论获取: 获取指定游戏的用户评论，支持多种筛选条件
游戏详情: 获取游戏的基本信息、价格、标签等
多语言支持: 支持中文、英文、日文、韩文等多种语言
MCP 集成: 完全兼容 MCP 协议，可与支持 MCP 的 AI 模型集成
Related MCP server: steam-mcp
克隆项目并安装依赖：
git clone <repository-url>
cd steamMCP
npm install构建项目：
npm run buildnpm startnpm run dev src/examples/example.ts配置你的 MCP 客户端，添加以下配置：
{
"mcpServers": {
"steam": {
"command": "node",
"args": ["dist/index.js"],
"cwd": "/path/to/steamMCP"
}
}
}获取 Steam 游戏的用户评论。
参数:
appId (必需): Steam 游戏的 App ID
language (可选): 评论语言，默认 schinese
filter (可选): 评论筛选，可选值: all, recent, updated
reviewType (可选): 评论类型，可选值: all, positive, negative
purchaseType (可选): 购买类型，可选值: all, non_steam_purchase, steam
numPerPage (可选): 每页评论数量，默认 10，最大 50
offset (可选): 评论偏移量，默认 0
示例:
{
"name": "get_steam_reviews",
"arguments": {
"appId": "1091500",
"language": "schinese",
"reviewType": "positive",
"numPerPage": 20
}
}搜索 Steam 游戏。
参数:
query (必需): 搜索关键词
示例:
{
"name": "search_steam_games",
"arguments": {
"query": "Cyberpunk 2077"
}
}获取 Steam 游戏详细信息。
参数:
appId (必需): Steam 游戏的 App ID
示例:
{
"name": "get_steam_game_details",
"arguments": {
"appId": "1091500"
}
}steamMCP/
├── src/
│ ├── types/ # TypeScript 类型定义
│ ├── services/ # Steam 服务类
│ ├── mcp/ # MCP 服务器实现
│ ├── examples/ # 使用示例
│ └── index.ts # 主入口文件
├── package.json
├── tsconfig.json
└── README.mdTypeScript: 主要开发语言
MCP SDK: Model Context Protocol 官方 SDK
Axios: HTTP 请求库
Cheerio: HTML 解析库
Node.js: 运行环境
速率限制: 请合理控制请求频率，避免对 Steam 服务器造成过大压力
用户代理: 工具使用标准的浏览器 User-Agent，但建议遵守 Steam 的使用条款
错误处理: 所有网络请求都包含错误处理，确保工具的稳定性
语言支持: 默认支持中文，可根据需要调整语言设置
npm run devnpm testnpm run buildMIT License
欢迎提交 Issue 和 Pull Request！
初始版本发布
支持游戏评论获取
支持游戏搜索
支持游戏详情获取
完整的 MCP 协议支持
获取Steam游戏的评论和游戏信息。返回格式化的评论数据，包括评论分数、正面/负面数量、评论文本和基本游戏信息。
| Name | Required | Description | Default |
|---|---|---|---|
| appid | Yes | Steam应用ID | |
| filter | No | recent: 按创建时间排序, updated: 按最后更新时间排序, all: (默认) 按有用性排序 | all |
| language | No | 语言过滤器 (例如: english, french, schinese)。默认为所有语言。 | all |
| day_range | No | 从现在到n天前查找有用评论的范围。仅适用于all过滤器。 | |
| cursor | No | 评论以20个为一批返回，所以第一次传递*，然后传递响应中返回的cursor值用于下一批，等等。 | * |
| review_type | No | all: 所有评论 (默认), positive: 仅正面评论, negative: 仅负面评论 | all |
| purchase_type | No | all: 所有评论, non_steam_purchase: 未在Steam上付费购买产品的用户撰写的评论, steam: 在Steam上付费购买产品的用户撰写的评论 (默认) | steam |
| num_per_page | No | 要获取的评论数量，最大100，默认50 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It only mentions the output format (reviews, scores, counts, text, game info) but omits important details like pagination behavior beyond cursor, error handling for invalid appid, rate limits, or authentication needs. This is insufficient for a tool with 8 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence in Chinese. It is efficiently worded but lacks structural elements like front-loading the key action or separating usage notes. However, it remains functional and non-redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 8 parameters, no output schema, and the complexity of pagination (cursor) and filters (day_range only valid with 'all' filter), the description is incomplete. It does not clarify the interaction between 'day_range' and 'filter', nor how to use the 'cursor' for multi-page results. More context is needed for correct tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds value by summarizing the output (formatted review data) but does not explain parameter semantics beyond what the schema already provides. It neither enhances nor detracts from the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves Steam game reviews and game information, specifying the returned data includes review scores, positive/negative counts, review text, and basic game info. This distinguishes it from the sibling tool 'search_steam_game', which likely searches for games.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling 'search_steam_game'. It does not specify prerequisites, limitations, or alternative scenarios, leaving the agent to infer usage context from the schema alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
搜索Steam游戏并返回游戏列表
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | 搜索关键词 | |
| category | No | 游戏分类 | games |
| supportedlang | No | 支持的语言 | schinese |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description lacks behavioral details such as authentication needs, rate limits, or what happens with empty results. Only states 'search and return list'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded, but could be more structured to include additional context for parameters and usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, and description does not explain the structure of the returned list or the meaning of parameters like category and supportedlang. Incomplete for a search tool with 3 parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are described in the schema. Description adds no extra meaning beyond what the schema provides, meeting baseline expectations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool searches Steam games and returns a list, which is a specific verb+resource. It distinguishes from sibling 'get_steam_review'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not provide context for when to search vs. when to use get_steam_review.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get_steam_reviewsearch_steam_gameThe two tools have clearly distinct purposes: one searches for games and the other retrieves reviews for a specific game. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern using snake_case (get_steam_review, search_steam_game), making them predictable and easy to understand.
With only 2 tools, the server feels minimal. While it covers search and reviews for a Steam-focused server, it is on the lower end of the typical range and may leave users wanting more functionality.
The server covers searching for games and getting reviews, but lacks common operations like retrieving detailed game info, user library, or recommendations, creating notable gaps for a complete Steam experience.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Gamedeals MCP — wraps CheapShark API (game deal aggregator, no auth required)
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
MCP server for Russian books search, details, and recommendation candidates.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Whatp/steam-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server