← 返回
未分类 中文

Exa Researcher

Comprehensive research capabilities using Exa AI MCP tools. Use when you need to conduct web research, gather company information, find people, extract code...
使用 Exa AI MCP 工具的综合研究能力。适用于网络调研、公司信息收集、人员查找、代码提取等场景。
sy2ruto sy2ruto 来源
未分类 clawhub v1.0.0 1 版本 99470.9 Key: 无需
★ 0
Stars
📥 188
下载
💾 0
安装
1
版本
#latest

概述

Exa Researcher

Overview

Exa Researcher provides powerful research capabilities through Exa AI's MCP tools, including web searches (basic and advanced), company and people research, code context extraction, web crawling, and deep research workflows.

Core Capabilities

1. Web Search (Basic & Advanced)

Basic Web Search (web_search_exa)

  • Quick web searches for general information
  • Ideal for: factual queries, news, quick facts

Advanced Web Search (web_search_advanced_exa)

  • More sophisticated search with filters and ranking
  • Ideal for: detailed research, finding specific content types, narrowing results by freshness, region, etc.

2. Company Research (company_research_exa)

  • Gather comprehensive information about companies
  • Ideal for: competitive analysis, partner research, due diligence
  • Use cases: company overview, financial data, recent news, leadership, products/services

3. People Search (people_search_exa)

  • Find information about people by name or query
  • Ideal for: background research, networking, finding experts
  • Use cases: professional backgrounds, expertise areas, recent activity

4. Code Context (get_code_context_exa)

  • Extract code context and technical information
  • Ideal for: technical research, understanding codebases, finding code examples
  • Use cases: understanding APIs, finding implementation patterns, technical documentation research

5. Web Crawling (crawling_exa)

  • Systematic web crawling for comprehensive information gathering
  • Ideal for: in-depth site research, content extraction, archiving
  • Use cases: website analysis, content aggregation, research from specific domains

6. Deep Research (deep_researcher_start, deep_researcher_check)

  • Long-running research workflows with progress tracking
  • Ideal for: comprehensive multi-source research, trend analysis, information synthesis
  • Use cases: research papers, market reports, feasibility studies, competitive intelligence

Usage Guidelines

When to Use Each Tool

TaskRecommended ToolReason
--------------------------------
Quick facts, newsweb_search_exaFast, simple queries
Detailed research with filtersweb_search_advanced_exaMore control, better results
Company analysiscompany_research_exaStructured company data
Finding people/expertspeople_search_exaPeople-focused search
Technical/code researchget_code_context_exaCode and API focused
Researching websites/domainscrawling_exaSystematic site exploration
Long-term research projectsdeep_researcher_startdeep_researcher_checkMulti-source, time-consuming

Research Workflow

  1. Identify the research goal - What information do you need?
  2. Select the appropriate tool - Match the task to the tool above
  3. Execute the search/research - Call the Exa AI tool
  4. Analyze results - Synthesize findings
  5. Iterate if needed - Refine queries or use additional tools

Advanced Use Cases

Competitive Analysis

  • Use company_research_exa for multiple competitors
  • Combine with web_search_advanced_exa for recent news
  • Document findings in structured format

Market Research

  • web_search_advanced_exa for market trends
  • crawling_exa for industry reports and whitepapers
  • Synthesize findings into market overview

Technical Documentation Research

  • get_code_context_exa for API documentation
  • Find code examples and implementation patterns
  • Extract technical specifications

Background Research (People/Companies)

  • people_search_exa for expertise matching
  • company_research_exa for organizational context
  • Combine for comprehensive profiles

Long-Form Research Projects

  • Use deep_researcher_start to initiate workflow
  • Monitor progress with deep_researcher_check
  • Let it run for complex, multi-source research needs

Tips for Best Results

  • Be specific with queries - More precise queries yield better results
  • Combine tools - Multiple tools can provide comprehensive coverage
  • Use filters wisely - Especially with advanced search (date ranges, regions, etc.)
  • Iterate - Refine queries based on initial results
  • Store important findings - Save significant research to memory
  • Consider search volume - Complex searches may take longer

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-05-12 06:05 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,082 📥 811,113
dev-programming

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 676 📥 325,528
ai-agent

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,227 📥 267,939