exa-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Exa Search

Exa搜索

Neural search for web content, code, companies, and people via the Exa MCP server.

通过Exa MCP服务器实现面向网页内容、代码、企业和人物的神经搜索。

When to Activate

适用场景

User needs current web information or news
Searching for code examples, API docs, or technical references
Researching companies, competitors, or market players
Finding professional profiles or people in a domain
Running background research for any development task
User says "search for", "look up", "find", or "what's the latest on"

用户需要最新的网页资讯或新闻
查找代码示例、API文档或技术参考资料
调研企业、竞争对手或市场参与者
查找特定领域的专业人士资料或个人简介
为各类开发任务开展背景调研
用户提出“搜索”、“查找”、“查询”或“最新动态是什么”等需求

MCP Requirement

MCP配置要求

Exa MCP server must be configured. Add to

~/.claude.json

json

"exa-web-search": {
  "command": "npx",
  "args": [
    "-y",
    "exa-mcp-server",
    "tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"
  ],
  "env": { "EXA_API_KEY": "YOUR_EXA_API_KEY_HERE" }
}

Get an API key at exa.ai. If you omit the

tools=...

argument, only a smaller default tool set may be enabled.

必须配置Exa MCP服务器。在

~/.claude.json

中添加以下内容：

json

"exa-web-search": {
  "command": "npx",
  "args": [
    "-y",
    "exa-mcp-server",
    "tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"
  ],
  "env": { "EXA_API_KEY": "YOUR_EXA_API_KEY_HERE" }
}

可在exa.ai获取API密钥。如果省略

tools=...

参数，仅会启用一组规模较小的默认工具。

Core Tools

核心工具

web_search_exa

General web search for current information, news, or facts.

web_search_exa(query: "latest AI developments 2026", numResults: 5)

Parameters:

Param	Type	Default	Notes
`query`	string	required	Search query
`numResults`	number	8	Number of results

用于获取最新资讯、新闻或事实的通用网页搜索工具。

web_search_exa(query: "latest AI developments 2026", numResults: 5)

参数说明：

Param	Type	Default	Notes
`query`	string	必填	搜索查询词
`numResults`	number	8	结果数量

web_search_advanced_exa

Filtered search with domain and date constraints.

web_search_advanced_exa(
  query: "React Server Components best practices",
  numResults: 5,
  includeDomains: ["github.com", "react.dev"],
  startPublishedDate: "2025-01-01"
)

Parameters:

Param	Type	Default	Notes
`query`	string	required	Search query
`numResults`	number	8	Number of results
`includeDomains`	string[]	none	Limit to specific domains
`excludeDomains`	string[]	none	Exclude specific domains
`startPublishedDate`	string	none	ISO date filter (start)
`endPublishedDate`	string	none	ISO date filter (end)

支持域名和日期筛选的高级搜索工具。

web_search_advanced_exa(
  query: "React Server Components best practices",
  numResults: 5,
  includeDomains: ["github.com", "react.dev"],
  startPublishedDate: "2025-01-01"
)

参数说明：

Param	Type	Default	Notes
`query`	string	必填	搜索查询词
`numResults`	number	8	结果数量
`includeDomains`	string[]	无	限定搜索的域名
`excludeDomains`	string[]	无	排除的域名
`startPublishedDate`	string	无	起始日期筛选（ISO格式）
`endPublishedDate`	string	无	结束日期筛选（ISO格式）

get_code_context_exa

Find code examples and documentation from GitHub, Stack Overflow, and docs sites.

get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000)

Parameters:

Param	Type	Default	Notes
`query`	string	required	Code or API search query
`tokensNum`	number	5000	Content tokens (1000-50000)

从GitHub、Stack Overflow和文档网站查找代码示例及文档。

get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000)

参数说明：

Param	Type	Default	Notes
`query`	string	必填	代码或API搜索查询词
`tokensNum`	number	5000	内容令牌数（范围1000-50000）

company_research_exa

Research companies for business intelligence and news.

company_research_exa(companyName: "Anthropic", numResults: 5)

Parameters:

Param	Type	Default	Notes
`companyName`	string	required	Company name
`numResults`	number	5	Number of results

用于商业情报和新闻的企业调研工具。

company_research_exa(companyName: "Anthropic", numResults: 5)

参数说明：

Param	Type	Default	Notes
`companyName`	string	必填	企业名称
`numResults`	number	5	结果数量

people_search_exa

Find professional profiles and bios.

people_search_exa(query: "AI safety researchers at Anthropic", numResults: 5)

查找专业人士的资料和简介。

people_search_exa(query: "AI safety researchers at Anthropic", numResults: 5)

crawling_exa

Extract full page content from a URL.

crawling_exa(url: "https://example.com/article", tokensNum: 5000)

Parameters:

Param	Type	Default	Notes
`url`	string	required	URL to extract
`tokensNum`	number	5000	Content tokens

从指定URL提取完整页面内容。

crawling_exa(url: "https://example.com/article", tokensNum: 5000)

参数说明：

Param	Type	Default	Notes
`url`	string	必填	待提取内容的URL
`tokensNum`	number	5000	内容令牌数

deep_researcher_start / deep_researcher_check

Start an AI research agent that runs asynchronously.

undefined

启动异步运行的AI调研代理。

undefined

Start research

启动调研

deep_researcher_start(query: "comprehensive analysis of AI code editors in 2026")

Check status (returns results when complete)

检查状态（完成后返回结果）

deep_researcher_check(researchId: "<id from start>")

undefined

deep_researcher_check(researchId: "<id from start>")

undefined

Usage Patterns

使用模式

Quick Lookup

快速查询

web_search_exa(query: "Node.js 22 new features", numResults: 3)

web_search_exa(query: "Node.js 22 new features", numResults: 3)

Code Research

代码调研

get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000)

get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000)

Company Due Diligence

企业尽职调查

company_research_exa(companyName: "Vercel", numResults: 5)
web_search_advanced_exa(query: "Vercel funding valuation 2026", numResults: 3)

company_research_exa(companyName: "Vercel", numResults: 5)
web_search_advanced_exa(query: "Vercel funding valuation 2026", numResults: 3)

Technical Deep Dive

技术深度调研

undefined

undefined

Start async research

启动异步调研

deep_researcher_start(query: "WebAssembly component model status and adoption")

... do other work ...

... 处理其他工作 ...

deep_researcher_check(researchId: "<id>")

undefined

deep_researcher_check(researchId: "<id>")

undefined

Tips

提示技巧

Use
```
web_search_exa
```
for broad queries,
```
web_search_advanced_exa
```
for filtered results
Lower
```
tokensNum
```
(1000-2000) for focused code snippets, higher (5000+) for comprehensive context

Combine

company_research_exa

with

web_search_advanced_exa

for thorough company analysis

Use
```
crawling_exa
```
to get full content from specific URLs found in search results
```
deep_researcher_start
```
is best for comprehensive topics that benefit from AI synthesis

宽泛查询使用
```
web_search_exa
```
，筛选结果使用
```
web_search_advanced_exa
```
若需聚焦代码片段，降低
```
tokensNum
```
至1000-2000；若需全面内容，设置为5000及以上

结合

company_research_exa

与

web_search_advanced_exa

进行全面的企业分析

使用
```
crawling_exa
```
提取搜索结果中特定URL的完整内容
```
deep_researcher_start
```
最适合需要AI综合分析的全面性主题

exa-search

Original

Translation

Exa Search

Exa搜索

When to Activate

适用场景

MCP Requirement

MCP配置要求

Core Tools

核心工具

web_search_exa

web_search_exa

web_search_advanced_exa

web_search_advanced_exa

get_code_context_exa

get_code_context_exa

company_research_exa

company_research_exa

people_search_exa

people_search_exa

crawling_exa

crawling_exa

deep_researcher_start / deep_researcher_check

deep_researcher_start / deep_researcher_check

Start research

启动调研

Check status (returns results when complete)

检查状态（完成后返回结果）

Usage Patterns

使用模式

Quick Lookup

快速查询

Code Research

代码调研

Company Due Diligence

企业尽职调查

Technical Deep Dive

技术深度调研

Start async research

启动异步调研

... do other work ...

... 处理其他工作 ...

Tips

提示技巧

Related Skills

相关技能