Provides tools to search for items and get item details from the Goofish (闲鱼) platform, which uses Taobao's mtop API.
Click on "Deploy 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., "@Goofish MCP Server search for Nintendo Switch games"
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.
独立的 Goofish / 闲鱼 MCP server，使用 Node.js + Playwright，并通过页面上下文里的 window.lib.mtop.request(...) 获取搜索数据。
✅ search_items：已按真实 Goofish 页面 + mtop 路线实现
✅ get_item_detail：已接入 mtop.taobao.idle.pc.detail，可结构化返回价格、卖家、地区、图片、属性、描述
✅ monitor_keyword：复用 search_items
✅ 浏览器登录态持久化：使用 Playwright persistent context
Related MCP server: xianyu-buyer-mcp
cd goofish-mcp-server
npm installnpm start默认使用：
浏览器 profile 目录：./.profiles/goofish
非 headless
可选环境变量：
GOOFISH_PROFILE_DIR=/path/to/profile
GOOFISH_HEADLESS=1首次启动时会打开浏览器 profile。 你需要在这个 profile 里手动登录 Goofish 一次。 后续 session 会复用该登录态。
输入：
{
"keyword": "iphone 15 pro",
"limit": 10
}输入：
{
"item_id": "1234567890"
}或：
{
"url": "https://www.goofish.com/item?id=1234567890"
}输入：
{
"keyword": "iphone 15 pro",
"max_items": 20,
"dedupe_key": "item_id"
}把这个进程作为 stdio MCP server 挂进去即可。
配置示例文件：
mcp-config-examples.json
Claude Desktop 核心思路：
{
"mcpServers": {
"goofish": {
"command": "node",
"args": ["/absolute/path/to/goofish-mcp-server/index.js"],
"env": {
"GOOFISH_PROFILE_DIR": "/absolute/path/to/goofish-mcp-server/.profiles/goofish",
"GOOFISH_HEADLESS": "0"
}
}
}
}补强 get_item_detail 的真实结构化字段
增加 cookie/export/import 管理
增加自动登录检测和错误提示
增加 remote/http transport
Get Goofish/Xianyu item detail by item_id or URL.
| Name | Required | Description | Default |
|---|---|---|---|
| item_id | No | ||
| url | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It indicates a read operation but lacks details on authentication, rate limits, or other behavioral traits beyond the basic get.
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 conveying the core purpose without extraneous words. Efficient and front-loaded.
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?
Adequate for a simple tool with two parameters, but lacks details on return values, error cases, or limitations. Could be more complete given no output schema.
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 0%, requiring the description to compensate. It mentions 'by item_id or URL' but does not add meaning beyond the schema's anyOf constraint, such as formats or priorities.
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?
Clearly states the action 'Get' and the resource 'Goofish/Xianyu item detail', distinguishing it from sibling tools like monitor_keyword, publish_item, and search_items.
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 explicit guidance on when to use or alternatives. The sibling tools imply distinct purposes, but the description does not discuss exclusions or preferred scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a normalized Goofish/Xianyu keyword snapshot for monitoring.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | ||
| max_items | No | ||
| dedupe_key | No | item_id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral aspects. It fails to mention whether the tool is read-only, cached, or has side effects. The term 'snapshot' implies a point-in-time view, but no further context is given.
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 short sentence, which is concise in length but lacks sufficient detail. It could be restructured to include essential information without being overly verbose.
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?
With no output schema, no parameter descriptions, and no annotations, the description is critically incomplete. It does not specify the format or content of the snapshot, making it hard for an agent to use effectively.
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 0% with no parameter descriptions in the schema. The description does not explain any of the three parameters (keyword, max_items, dedupe_key), leaving their purpose ambiguous.
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 states it returns a normalized keyword snapshot for monitoring, identifying the action and resource. However, it does not explain what 'normalized' means or how it differs from similar tools like search_items, which also return keyword-related results.
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 offers no guidance on when to use this tool versus alternatives like search_items or get_item_detail. It only mentions 'for monitoring' without clarifying conditions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Publish a new Goofish/Xianyu second-hand item listing.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | 商品标题 | |
| desc | Yes | 商品描述 | |
| price_yuan | Yes | 售价（元），如 99.5 | |
| category_id | No | 分类ID（可选） | |
| images | No | 图片本地路径列表（如 /tmp/img.jpg），可选 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description merely states 'Publish' without disclosing behavioral traits like authentication needs, side effects, or whether the operation is reversible.
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 with no unnecessary words, efficiently conveying the tool's purpose.
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 the tool has 5 parameters and no output schema, the description lacks essential details such as return values, error handling, or behavior on success/failure, and does not differentiate from sibling tools.
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 the baseline is 3; the description adds no additional meaning beyond the schema’s basic parameter descriptions.
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 verb 'Publish' and the resource 'Goofish/Xianyu second-hand item listing', distinguishing it from sibling tools like get_item_detail, monitor_keyword, and search_items.
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 usage guidelines are provided; the description does not explain when to use this tool, prerequisites, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Goofish/Xianyu items by keyword using a logged-in Playwright browser context. Example queries: iphone 15 pro, sony a7, dyson v12.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. Only mentions automation context but omits details on rate limits, blocking risks, session requirements, or return format. Insufficient for being the sole source.
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?
One sentence with relevant examples, no fluff. Every part adds value.
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?
Describes the basic action and prerequisite, but for a 2-param search tool with no output schema, it should hint at return structure or pagination. Leaves agent guessing about results.
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 0%, but description only mentions keyword via examples, not its format or required roles. Limit parameter and its default are completely ignored. Fails to compensate for missing schema descriptions.
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?
Clearly states verb 'Search' and resource 'Goofish/Xianyu items' via unique context 'logged-in Playwright browser context'. Distinct from siblings like get_item_detail or monitor_keyword.
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?
Implies prerequisite (logged-in Playwright context) but lacks explicit when-to-use vs alternatives like monitor_keyword or get_item_detail. Example queries help but no exclusion criteria.
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.
v1.0.0get_item_detailmonitor_keywordpublish_itemsearch_itemsScored across 4 tools
Each tool has a clearly distinct purpose: one for getting item details, one for setting up keyword monitoring, one for publishing items, and one for searching. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (get_item_detail, monitor_keyword, publish_item, search_items), making them predictable and easy to understand.
With 4 tools covering search, detail retrieval, publishing, and monitoring, the set is well-scoped for its domain without being excessive or insufficient.
While the server covers search, detail, publish, and monitoring, it lacks update and delete capabilities, leaving a notable gap in the full lifecycle of item management.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
搜索笔记、浏览首页推荐、查看笔记内容与评论，并发表你的评论。直接在工作流中与小红书内容互动，高效跟进话题。
Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
Structured web research tool for AI agents: search, fetch and shape web data into the JSON schema…