anysearch-mcp-server

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AnySearch MCP Server Skill

Skill by ara.so — MCP Skills collection.

AnySearch MCP Server is a unified real-time search engine for AI agents, providing general web search, 23 vertical domain searches (finance, academic, security, legal, code, etc.), parallel batch search, and full-page URL content extraction via the MCP protocol.

由ara.so开发的Skill — MCP Skills合集。

AnySearch MCP Server 是面向AI Agent的统一实时搜索引擎，通过MCP协议提供通用网页搜索、23个垂直领域搜索（金融、学术、安全、法律、代码等）、并行批量搜索以及全页面URL内容提取功能。

What It Does

功能介绍

General Web Search: Natural language queries across the web
Vertical Domain Search: Structured queries in 23 specialized domains
Batch Search: Execute up to 5 independent queries in parallel
URL Extraction: Fetch and convert full page content to Markdown
Anonymous Access: Works without API key (lower rate limits)

通用网页搜索：支持自然语言的全网查询
垂直领域搜索：23个专业领域的结构化查询
批量搜索：并行执行最多5个独立查询
URL提取：获取完整页面内容并转换为Markdown格式
匿名访问：无需API密钥即可使用（速率限制较低）

Installation

安装

Streamable HTTP (Recommended - No Proxy)

Streamable HTTP（推荐 - 无需代理）

For agents supporting MCP spec 2025-03-26+ (OpenCode, Claude Desktop 2025.6+):

OpenCode (

~/.opencode/config.json

opencode.json

json

{
  "mcp": {
    "anysearch": {
      "type": "streamable-http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ANYSEARCH_API_KEY}"
      }
    }
  }
}

Claude Desktop (

claude_desktop_config.json

json

{
  "mcpServers": {
    "anysearch": {
      "type": "streamable-http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ANYSEARCH_API_KEY}"
      }
    }
  }
}

适用于支持MCP规范2025-03-26+的Agent（OpenCode、Claude Desktop 2025.6+）：

OpenCode（

~/.opencode/config.json

或

opencode.json

）：

json

{
  "mcp": {
    "anysearch": {
      "type": "streamable-http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ANYSEARCH_API_KEY}"
      }
    }
  }
}

Claude Desktop（

claude_desktop_config.json

）：

json

{
  "mcpServers": {
    "anysearch": {
      "type": "streamable-http",
      "url": "https://api.anysearch.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ANYSEARCH_API_KEY}"
      }
    }
  }
}

stdio Transport (Via mcp-remote Proxy)

stdio 传输（通过mcp-remote代理）

Claude Desktop (

claude_desktop_config.json

json

{
  "mcpServers": {
    "anysearch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

VS Code Copilot (

.vscode/mcp.json

json

{
  "servers": {
    "anysearch": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

Cline (VS Code settings):

json

{
  "mcpServers": {
    "anysearch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

Claude Desktop（

claude_desktop_config.json

）：

json

{
  "mcpServers": {
    "anysearch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

VS Code Copilot（

.vscode/mcp.json

）：

json

{
  "servers": {
    "anysearch": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

Cline（VS Code 设置）：

json

{
  "mcpServers": {
    "anysearch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.anysearch.com/mcp",
        "--header",
        "Authorization: Bearer ${ANYSEARCH_API_KEY}"
      ]
    }
  }
}

SSE Transport (Via supergateway Proxy)

SSE 传输（通过supergateway代理）

Start the proxy server:

bash

npx -y supergateway \
  --streamableHttp https://api.anysearch.com/mcp \
  --outputTransport sse \
  --port 8000 \
  --oauth2Bearer ${ANYSEARCH_API_KEY}

Cursor (

.cursor/mcp.json

json

{
  "mcpServers": {
    "anysearch": {
      "type": "sse",
      "url": "http://localhost:8000/sse"
    }
  }
}

Windsurf (

~/.codeium/windsurf/mcp_config.json

json

{
  "mcpServers": {
    "anysearch": {
      "serverUrl": "http://localhost:8000/sse"
    }
  }
}

启动代理服务器：

bash

npx -y supergateway \
  --streamableHttp https://api.anysearch.com/mcp \
  --outputTransport sse \
  --port 8000 \
  --oauth2Bearer ${ANYSEARCH_API_KEY}

Cursor（

.cursor/mcp.json

）：

json

{
  "mcpServers": {
    "anysearch": {
      "type": "sse",
      "url": "http://localhost:8000/sse"
    }
  }
}

Windsurf（

~/.codeium/windsurf/mcp_config.json

）：

json

{
  "mcpServers": {
    "anysearch": {
      "serverUrl": "http://localhost:8000/sse"
    }
  }
}

API Key Configuration

API密钥配置

Optional but recommended. Get a free key at: https://anysearch.com/console/api-keys

Priority order:

```
Authorization
```
header /
```
--api_key
```
flag
```
ANYSEARCH_API_KEY
```
environment variable
```
.env
```
file with
```
ANYSEARCH_API_KEY=<key>
```
Anonymous access (lower rate limits)

Set environment variable:

bash

export ANYSEARCH_API_KEY="your-api-key-here"

Or create

.env

file:

ANYSEARCH_API_KEY=your-api-key-here

可选但推荐。在以下地址获取免费密钥：https://anysearch.com/console/api-keys

优先级顺序：

```
Authorization
```
请求头 /
```
--api_key
```
参数
```
ANYSEARCH_API_KEY
```
环境变量
包含
```
ANYSEARCH_API_KEY=<key>
```
的
```
.env
```
文件
匿名访问（速率限制较低）

设置环境变量：

bash

export ANYSEARCH_API_KEY="your-api-key-here"

或创建

.env

文件：

ANYSEARCH_API_KEY=your-api-key-here

Available Tools

可用工具

search

- General or Vertical Domain Search

search

- 通用或垂直领域搜索

Execute a search query. For vertical searches, you MUST call

list_domains

first.

Parameters:

Parameter	Type	Required	Description
`query`	string	Yes	Search query (format depends on domain)
`domain`	string	No	Vertical domain (e.g., `finance` , `academic` )
`sub_domain`	string	No	Sub-domain routing key (required for vertical)
`sub_domain_params`	object	No	Extra params per sub_domain schema
`content_types`	array	No	Filter: `web` , `news` , `code` , `doc` , etc.
`zone`	string	No	`cn` or `intl` (required when sub_domain requires)
`max_results`	integer	No	1-100, default 10
`freshness`	string	No	`day` , `week` , `month` , `year`

General Web Search Example:

json

{
  "query": "quantum computing breakthroughs 2025",
  "max_results": 5,
  "freshness": "month"
}

Vertical Search Example (Stock):

First, call

list_domains

json

{
  "domain": "finance"
}

Then use the discovered

sub_domain

and

query_format

json

{
  "query": "AAPL",
  "domain": "finance",
  "sub_domain": "finance.us_stock",
  "max_results": 5
}

News Search Example:

json

{
  "query": "artificial intelligence",
  "content_types": ["news"],
  "freshness": "week",
  "max_results": 10
}

Academic Search Example:

json

{
  "query": "10.1038/s41586-019-1666-5",
  "domain": "academic",
  "sub_domain": "academic.doi"
}

执行搜索查询。进行垂直搜索前，必须先调用
list_domains
。

参数：

参数	类型	是否必填	描述
`query`	string	是	搜索查询（格式取决于领域）
`domain`	string	否	垂直领域（例如： `finance` 、 `academic` ）
`sub_domain`	string	否	子领域路由键（垂直搜索必填）
`sub_domain_params`	object	否	子领域对应的额外参数
`content_types`	array	否	过滤类型： `web` 、 `news` 、 `code` 、 `doc` 等
`zone`	string	否	`cn` 或 `intl` （部分子领域必填）
`max_results`	integer	否	1-100，默认值为10
`freshness`	string	否	`day` 、 `week` 、 `month` 、 `year`

通用网页搜索示例：

json

{
  "query": "quantum computing breakthroughs 2025",
  "max_results": 5,
  "freshness": "month"
}

垂直搜索示例（股票）：

首先，调用

list_domains

：

json

{
  "domain": "finance"
}

然后使用返回的

sub_domain

和

query_format

：

json

{
  "query": "AAPL",
  "domain": "finance",
  "sub_domain": "finance.us_stock",
  "max_results": 5
}

新闻搜索示例：

json

{
  "query": "artificial intelligence",
  "content_types": ["news"],
  "freshness": "week",
  "max_results": 10
}

学术搜索示例：

json

{
  "query": "10.1038/s41586-019-1666-5",
  "domain": "academic",
  "sub_domain": "academic.doi"
}

list_domains

- Query Vertical Domain Directory

list_domains

- 查询垂直领域目录

MUST be called before vertical search to discover available sub_domains and their query formats.

Parameters:

Parameter	Type	Required	Description
`domain`	string	One of	Single domain to query
`domains`	array	One of	Batch up to 5 domains

Single Domain Example:

json

{
  "domain": "finance"
}

Multiple Domains Example:

json

{
  "domains": ["finance", "academic", "security"]
}

Returns Markdown table with:

```
sub_domain
```
: Routing key for search
```
description
```
: What the sub_domain searches
```
query_format
```
: Exact format required (e.g., raw ticker, DOI)
```
params_schema
```
: JSON schema for optional parameters
```
zone
```
: If
```
CN
```
, must set
```
zone: "cn"
```
in search

垂直搜索前必须调用，用于发现可用的子领域及其查询格式。

参数：

参数	类型	是否必填	描述
`domain`	string	二选一	单个要查询的领域
`domains`	array	二选一	最多批量查询5个领域

单个领域示例：

json

{
  "domain": "finance"
}

多个领域示例：

json

{
  "domains": ["finance", "academic", "security"]
}

返回Markdown表格包含：

```
sub_domain
```
：搜索路由键
```
description
```
：子领域搜索范围
```
query_format
```
：要求的精确格式（例如：原始股票代码、DOI）
```
params_schema
```
：可选参数的JSON schema
```
zone
```
：若为
```
CN
```
，搜索时必须设置
```
zone: "cn"
```

batch_search

- Parallel Search Execution

batch_search

- 并行搜索执行

Execute 2-5 independent search queries in parallel. Single failure doesn't block others.

Parameters:

Parameter	Type	Required	Description
`queries`	array	Yes	1-5 query objects, each with same fields as `search`

Example:

json

{
  "queries": [
    {
      "query": "AAPL",
      "domain": "finance",
      "sub_domain": "finance.us_stock"
    },
    {
      "query": "python async http client",
      "domain": "code",
      "sub_domain": "code.general"
    },
    {
      "query": "CVE-2024-1234",
      "domain": "security",
      "sub_domain": "security.cve"
    }
  ]
}

并行执行2-5个独立搜索查询。单个查询失败不会阻塞其他查询。

参数：

参数	类型	是否必填	描述
`queries`	array	是	1-5个查询对象，每个对象包含与 `search` 相同的字段

示例：

json

{
  "queries": [
    {
      "query": "AAPL",
      "domain": "finance",
      "sub_domain": "finance.us_stock"
    },
    {
      "query": "python async http client",
      "domain": "code",
      "sub_domain": "code.general"
    },
    {
      "query": "CVE-2024-1234",
      "domain": "security",
      "sub_domain": "security.cve"
    }
  ]
}

extract

- URL Content Extraction

extract

- URL内容提取

Fetch full page content from a URL and return as Markdown. HTML pages only, truncated at 50,000 characters.

Parameters:

Parameter	Type	Required	Description
`url`	string	Yes	Target URL ( `http://` or `https://` )

Example:

json

{
  "url": "https://en.wikipedia.org/wiki/Quantum_computing"
}

获取URL的完整页面内容并以Markdown格式返回。仅支持HTML页面，超过50000字符会被截断。

参数：

参数	类型	是否必填	描述
`url`	string	是	目标URL（ `http://` 或 `https://` ）

示例：

json

{
  "url": "https://en.wikipedia.org/wiki/Quantum_computing"
}

Supported Domains

支持的领域

23 vertical domains available:

```
code
```
- Code repositories, packages, documentation
```
tech
```
- Technology news, products, reviews
```
fashion
```
- Fashion trends, brands, products
```
travel
```
- Flights, hotels, destinations
```
home
```
- Home improvement, furniture, decor
```
ecommerce
```
- Products, prices, reviews
```
gaming
```
- Games, platforms, news
```
film
```
- Movies, reviews, showtimes
```
music
```
- Songs, artists, albums
```
finance
```
- Stocks, crypto, markets, companies
```
academic
```
- Papers, patents, research
```
legal
```
- Laws, regulations, cases
```
business
```
- Companies, industries, markets
```
ip
```
- Patents, trademarks, copyrights
```
security
```
- CVEs, vulnerabilities, threats
```
education
```
- Courses, schools, materials
```
health
```
- Medical, wellness, drugs
```
religion
```
- Religious texts, organizations
```
geo
```
- Geographic data, maps, places
```
environment
```
- Climate, conservation, ecology
```
energy
```
- Energy sources, efficiency, policy
```
ugc
```
- User-generated content, forums

提供23个垂直领域：

```
code
```
- 代码仓库、包、文档
```
tech
```
- 科技新闻、产品、评测
```
fashion
```
- 时尚趋势、品牌、产品
```
travel
```
- 航班、酒店、目的地
```
home
```
- 家居装修、家具、装饰
```
ecommerce
```
- 产品、价格、评测
```
gaming
```
- 游戏、平台、新闻
```
film
```
- 电影、评测、放映时间
```
music
```
- 歌曲、艺人、专辑
```
finance
```
- 股票、加密货币、市场、公司
```
academic
```
- 论文、专利、研究
```
legal
```
- 法律、法规、案例
```
business
```
- 公司、行业、市场
```
ip
```
- 专利、商标、版权
```
security
```
- CVE、漏洞、威胁
```
education
```
- 课程、学校、资料
```
health
```
- 医疗、健康、药品
```
religion
```
- 宗教文本、组织
```
geo
```
- 地理数据、地图、地点
```
environment
```
- 气候、保护、生态
```
energy
```
- 能源来源、效率、政策
```
ugc
```
- 用户生成内容、论坛

Common Usage Patterns

常见使用模式

Pattern 1: General Web Search

模式1：通用网页搜索

When user asks an open-ended question:

json

{
  "query": "best practices for microservices architecture",
  "max_results": 10
}

当用户提出开放式问题时：

json

{
  "query": "best practices for microservices architecture",
  "max_results": 10
}

Pattern 2: Recent News

模式2：近期新闻

When user wants current information:

json

{
  "query": "SpaceX launches",
  "content_types": ["news"],
  "freshness": "week",
  "max_results": 5
}

当用户需要当前信息时：

json

{
  "query": "SpaceX launches",
  "content_types": ["news"],
  "freshness": "week",
  "max_results": 5
}

Pattern 3: Vertical Search Workflow

模式3：垂直搜索流程

When user mentions structured identifiers (stock ticker, CVE, DOI, etc.):

Step 1: Identify the domain and call

list_domains

json

{
  "domain": "security"
}

Step 2: Parse the response to find the correct

sub_domain

and

query_format

Step 3: Execute search with exact format

json

{
  "query": "CVE-2024-1234",
  "domain": "security",
  "sub_domain": "security.cve"
}

当用户提到结构化标识符（股票代码、CVE、DOI等）时：

步骤1： 识别领域并调用

list_domains

json

{
  "domain": "security"
}

步骤2： 解析响应以找到正确的

sub_domain

和

query_format

步骤3： 使用精确格式执行搜索

json

{
  "query": "CVE-2024-1234",
  "domain": "security",
  "sub_domain": "security.cve"
}

Pattern 4: Multi-Intent Queries

模式4：多意图查询

When user has multiple independent questions:

json

{
  "queries": [
    {
      "query": "TSLA",
      "domain": "finance",
      "sub_domain": "finance.us_stock"
    },
    {
      "query": "electric vehicle market trends",
      "freshness": "month"
    }
  ]
}

当用户有多个独立问题时：

json

{
  "queries": [
    {
      "query": "TSLA",
      "domain": "finance",
      "sub_domain": "finance.us_stock"
    },
    {
      "query": "electric vehicle market trends",
      "freshness": "month"
    }
  ]
}

Pattern 5: Deep Content Extraction

模式5：深度内容提取

When search results provide URLs but user needs full content:

Step 1: Search

json

{
  "query": "kubernetes best practices",
  "max_results": 3
}

Step 2: Extract top result

json

{
  "url": "https://kubernetes.io/docs/concepts/configuration/overview/"
}

当搜索结果提供URL但用户需要完整内容时：

步骤1： 搜索

json

{
  "query": "kubernetes best practices",
  "max_results": 3
}

步骤2： 提取顶部结果

json

{
  "url": "https://kubernetes.io/docs/concepts/configuration/overview/"
}

Pattern 6: Code Search

模式6：代码搜索

When user needs code examples:

json

{
  "query": "react hooks useEffect",
  "domain": "code",
  "sub_domain": "code.general",
  "max_results": 10
}

当用户需要代码示例时：

json

{
  "query": "react hooks useEffect",
  "domain": "code",
  "sub_domain": "code.general",
  "max_results": 10
}

Pattern 7: Academic Research

模式7：学术研究

When user references DOI or research topic:

json

{
  "query": "10.1038/nature12373",
  "domain": "academic",
  "sub_domain": "academic.doi"
}

当用户引用DOI或研究主题时：

json

{
  "query": "10.1038/nature12373",
  "domain": "academic",
  "sub_domain": "academic.doi"
}

Decision Flow

决策流程

Use this logic to choose the right tool:

User query
  |
  +-- Has structured identifiers? (ticker, CVE, DOI, IATA, patent, etc.)
  |     YES -> 1) list_domains(domain) -> discover sub_domain & query_format
  |             2) search with domain + sub_domain + exact format
  |
  +-- Multiple independent questions?
  |     YES -> batch_search with array of queries
  |
  +-- Need full article/page content beyond snippets?
  |     YES -> search -> extract(url) from results
  |
  +-- Filter by content type or freshness?
  |     YES -> search with content_types and/or freshness params
  |
  +-- Otherwise -> search (general, natural language)

使用以下逻辑选择合适的工具：

用户查询
  |
  +-- 是否包含结构化标识符？（股票代码、CVE、DOI、IATA、专利等）
  |     是 -> 1) 调用list_domains(domain) -> 发现sub_domain和query_format
  |             2) 使用domain + sub_domain + 精确格式执行搜索
  |
  +-- 是否为多个独立问题？
  |     是 -> 使用batch_search传入查询数组
  |
  +-- 是否需要搜索摘要之外的完整文章/页面内容？
  |     是 -> 先搜索 -> 从结果中提取url
  |
  +-- 是否需要按内容类型或时效性过滤？
  |     是 -> 使用content_types和/或freshness参数执行搜索
  |
  +-- 其他情况 -> 执行通用自然语言搜索

Vertical Search Requirements

垂直搜索要求

Before executing vertical search, you MUST:

Call
list_domains
for the target domain
Follow
query_format
exactly (e.g., raw ticker "AAPL", not "Apple stock")
Use correct
sub_domain
that matches user intent
Set
zone: "cn"
if the sub_domain requires it (check
```
zone
```
field)
Include
sub_domain_params
if the schema requires additional fields

执行垂直搜索前，必须：

**调用
```
list_domains
```
**获取目标领域信息
严格遵循
query_format
（例如：使用原始股票代码"AAPL"，而非"Apple stock"）
使用匹配用户意图的
sub_domain
若子领域要求，设置
zone: "cn"
（查看
```
zone
```
字段）
若schema要求，包含
sub_domain_params

Troubleshooting

故障排除

Issue: "Invalid query format for vertical search"

问题："Invalid query format for vertical search"

Cause: Query doesn't match the

query_format

from

list_domains

Solution:

Call
```
list_domains
```
for the domain
Check the
```
query_format
```
field
Transform user input to match exact format (e.g., extract ticker symbol from natural language)

原因： 查询格式与

list_domains

返回的

query_format

不匹配

解决方案：

调用
```
list_domains
```
获取该领域信息
查看
```
query_format
```
字段
将用户输入转换为精确格式（例如：从自然语言中提取股票代码）

Issue: "Missing required zone parameter"

问题："Missing required zone parameter"

Cause: Sub_domain requires

zone: "cn"

but it wasn't provided

Solution:

Check
```
list_domains
```
response for
```
zone
```
field
If
```
zone: "CN"
```
, add
```
"zone": "cn"
```
to search call

原因： 子领域需要

zone: "cn"

但未提供

解决方案：

查看
```
list_domains
```
响应中的
```
zone
```
字段
若
```
zone: "CN"
```
，在搜索请求中添加
```
"zone": "cn"
```

Issue: "Anonymous rate limit exceeded"

问题："Anonymous rate limit exceeded"

Cause: No API key configured, hitting lower anonymous limits

Solution:

Get free API key from https://anysearch.com/console/api-keys
Set
```
ANYSEARCH_API_KEY
```
environment variable
Restart agent to pick up new key

原因： 未配置API密钥，达到匿名访问的速率限制

解决方案：

在https://anysearch.com/console/api-keys获取免费API密钥
设置
```
ANYSEARCH_API_KEY
```
环境变量
重启Agent以加载新密钥

Issue: "SSE/stdio proxy not working"

问题："SSE/stdio proxy not working"

Cause: Proxy server not running or incorrect configuration

Solution for SSE:

Ensure

supergateway

proxy is running:

npx -y supergateway --streamableHttp https://api.anysearch.com/mcp --outputTransport sse --port 8000 --oauth2Bearer ${ANYSEARCH_API_KEY}

Check proxy is accessible:
```
curl http://localhost:8000/sse
```
Verify agent config points to
```
http://localhost:8000/sse
```

Solution for stdio:

Use
```
mcp-remote
```
proxy (simpler, auto-detects transport)
Verify
```
npx
```
can download packages
Check agent restart picked up new config

原因： 代理服务器未运行或配置错误

SSE解决方案：

确保

supergateway

代理正在运行：

npx -y supergateway --streamableHttp https://api.anysearch.com/mcp --outputTransport sse --port 8000 --oauth2Bearer ${ANYSEARCH_API_KEY}

检查代理是否可访问：
```
curl http://localhost:8000/sse
```
验证Agent配置指向
```
http://localhost:8000/sse
```

stdio解决方案：

使用
```
mcp-remote
```
代理（更简单，自动检测传输方式）
验证
```
npx
```
可下载包
检查Agent重启后是否加载了新配置

Issue: "No results for vertical search"

问题："No results for vertical search"

Cause: Wrong

sub_domain

selected or malformed query

Solution:

Review
```
list_domains
```
output again
Match user intent to
```
description
```
field of sub_domains
Verify query matches
```
query_format
```
exactly
Try general search first to validate the entity exists

原因： 选择了错误的

sub_domain

或查询格式错误

解决方案：

重新查看
```
list_domains
```
输出
将用户意图与子领域的
```
description
```
字段匹配
验证查询是否完全符合
```
query_format
```
先尝试通用搜索验证实体是否存在

Issue: "Extract returns truncated content"

问题："Extract returns truncated content"

Cause: Page content exceeds 50,000 character limit

Solution:

This is expected behavior for very long pages
Use search results snippets for overview
Extract multiple specific URLs if needed
For extremely long docs, consider asking user which sections to prioritize

原因： 页面内容超过50000字符限制

解决方案：

这是超长页面的预期行为
使用搜索摘要获取概述
若需要，提取多个特定URL
对于极长文档，可询问用户优先关注哪些部分

Configuration Quick Reference

配置快速参考

Agent	Transport	Proxy?	Config File
OpenCode	Streamable HTTP	No	`opencode.json`
Claude Desktop 2025.6+	Streamable HTTP	No	`claude_desktop_config.json`
Claude Desktop (legacy)	stdio	Yes (mcp-remote)	`claude_desktop_config.json`
VS Code Copilot	stdio	Yes (mcp-remote)	`.vscode/mcp.json`
Cline	stdio	Yes (mcp-remote)	VS Code settings
Cursor	SSE	Yes (supergateway)	`.cursor/mcp.json`
Windsurf	SSE	Yes (supergateway)	`mcp_config.json`

Agent	传输方式	是否需要代理	配置文件
OpenCode	Streamable HTTP	否	`opencode.json`
Claude Desktop 2025.6+	Streamable HTTP	否	`claude_desktop_config.json`
Claude Desktop（旧版）	stdio	是（mcp-remote）	`claude_desktop_config.json`
VS Code Copilot	stdio	是（mcp-remote）	`.vscode/mcp.json`
Cline	stdio	是（mcp-remote）	VS Code 设置
Cursor	SSE	是（supergateway）	`.cursor/mcp.json`
Windsurf	SSE	是（supergateway）	`mcp_config.json`

Best Practices

最佳实践

Always call
list_domains
before vertical search - Don't assume you know the sub_domains
Use batch_search for multiple intents - More efficient than sequential calls
Prefer general search for exploratory queries - Vertical search requires exact formats
Extract URLs sparingly - Search snippets are often sufficient
Set appropriate
max_results
- Default 10 is good, reduce for speed, increase for thoroughness
Use
freshness
for time-sensitive queries - News, events, recent developments
Never include API keys in chat - Always use environment variables
Check zone requirements - CN sub_domains require
```
zone: "cn"
```
parameter

垂直搜索前务必调用
list_domains
- 不要假设已知子领域信息
多意图查询使用batch_search - 比顺序调用更高效
探索性查询优先使用通用搜索 - 垂直搜索需要精确格式
谨慎使用URL提取 - 搜索摘要通常已足够
设置合适的
max_results
- 默认10即可，减少值提升速度，增加值提高全面性
时效性查询使用
freshness
- 新闻、事件、最新进展
聊天中绝不包含API密钥 - 始终使用环境变量
检查区域要求 - CN子领域需要
```
zone: "cn"
```
参数

Security Notes

安全说明

All queries and URLs are sent to
```
https://api.anysearch.com
```
Do not use for sensitive data (passwords, personal info, trade secrets)
API keys grant higher rate limits - protect them as secrets
Anonymous access works but has lower limits

所有查询和URL均发送至
```
https://api.anysearch.com
```
请勿用于敏感数据（密码、个人信息、商业机密）
API密钥可提升速率限制 - 需妥善保管
匿名访问可用但速率限制较低