agentleFS
Sign inStart free
wangfeiwest2025wangfeiwest2025/openclaw-integration-skills/exa-mcp/SKILL.md

exa-mcp

Skill0 starsChanged 9 months agoMITView on GitHub

Use Exa's AI-powered search tools via MCP for web search, code search, company research, people search, web crawling, and deep research. Activate when user needs to search the web, find code examples, research companies, find people profiles, extract webpage content, or conduct in-depth research with reports.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search the web for any topic and get clean, ready-to-use content.

    line 32
  2. Distinctive:

    Start an AI research agent that searches, reads, and writes a detailed report.

    line 86
  3. Distinctive:

    Check status and get results from a deep research task.

    line 95
  4. Distinctive:

    Start simple: Use core tools (web_search_exa, get_code_context_exa, company_research_exa) first

    line 146
  5. Distinctive:

    Advanced filters: Use web_search_advanced_exa only when you need specific controls

    line 147
  6. Distinctive:

    Deep research: Use deep_researcher_start for complex topics requiring synthesis

    line 148
  7. Distinctive:

    Known URLs: Use crawling_exa when you have the exact URL, not for discovery

    line 149
  8. Distinctive:

    People search: Use people_search_exa for professional profiles and experts

    line 150
  9. Distinctive:

    Always check: Use deep_researcher_check to monitor long-running research tasks

    line 151

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Exa MCP - AI-Powered Search Tools

Exa MCP provides AI-optimized search capabilities through multiple specialized tools. Use when you need to search the web, find code examples, research companies, locate people, crawl specific content, or conduct deep research.

Configuration

MCP Server URL:

https://mcp.exa.ai/mcp

To enable all tools (as configured):

https://mcp.exa.ai/mcp?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

For your own API key (to exceed free limits):

https://mcp.exa.ai/mcp?exaApiKey=YOUR_EXA_KEY

Available Tools

Core Tools (Always Available)

1. web_search_exa - Web Search

Search the web for any topic and get clean, ready-to-use content.

Use when: User asks to search the web, find recent news, research a topic, get information about anything.

Best for: General web searches, news, articles, blog posts, documentation.

2. get_code_context_exa - Code Search

Find code examples, documentation, and programming solutions from GitHub, Stack Overflow, and developer documentation.

Use when: User needs code examples, API documentation, programming tutorials, or wants to learn how to implement something.

Best for: Finding code snippets, learning new APIs, debugging with examples, exploring open source projects.

3. company_research_exa - Company Research

Research any company to get business information, news, and insights.

Use when: User asks about a company, wants business information, company news, or competitive analysis.

Best for: Company overviews, product information, recent news, financial insights, competitive intelligence.

Advanced Tools (Available)

4. web_search_advanced_exa - Advanced Web Search

Advanced web search with full control over filters, domains, dates, and content options.

Use when: Need precise search with specific filters, date ranges, domain exclusions/inclusions, or content type preferences.

Best for: Targeted research, technical searches, domain-specific content, time-sensitive queries.

5. crawling_exa - Webpage Crawling

Get the full content of a specific webpage from a known URL.

Use when: User provides a specific URL and wants the complete content extracted.

Best for: Extracting full article content, reading documentation pages, processing specific URLs.

6. people_search_exa - People Search

Find people and their professional profiles.

Use when: User needs to find someone's LinkedIn profile, professional background, or identify experts in a field.

Best for: Finding professionals, locating experts, professional networking, background research.

7. deep_researcher_start - Start Deep Research

Start an AI research agent that searches, reads, and writes a detailed report.

Use when: User needs comprehensive research on a complex topic that requires multiple sources and synthesis.

Best for: In-depth reports, comprehensive research, multi-source synthesis, detailed analysis.

8. deep_researcher_check - Check Deep Research

Check status and get results from a deep research task.

Use when: Started a deep research task and need to check progress or retrieve results.

Usage Patterns

Pattern 1: Simple Web Search

User: "What's the latest news about AI agents?"
→ Use: web_search_exa
Query: "latest news about AI agents"

Pattern 2: Code Examples

User: "Show me how to implement OAuth 2.0 in Python"
→ Use: get_code_context_exa
Query: "OAuth 2.0 implementation Python"

Pattern 3: Company Research

User: "Tell me about Stripe's products and recent news"
→ Use: company_research_exa
Query: "Stripe"

Pattern 4: People Search

User: "Find experts in quantum computing"
→ Use: people_search_exa
Query: "quantum computing experts"

Pattern 5: Extract URL Content

User: "Read this article: https://example.com/article"
→ Use: crawling_exa
URL: "https://example.com/article"

Pattern 6: Deep Research Flow

User: "Create a detailed report on quantum computing startups"
→ Step 1: Use deep_researcher_start with detailed query
→ Step 2: Use deep_researcher_check to monitor progress
→ Step 3: Retrieve final report when complete

Best Practices

  1. Start simple: Use core tools (web_search_exa, get_code_context_exa, company_research_exa) first
  2. Advanced filters: Use web_search_advanced_exa only when you need specific controls
  3. Deep research: Use deep_researcher_start for complex topics requiring synthesis
  4. Known URLs: Use crawling_exa when you have the exact URL, not for discovery
  5. People search: Use people_search_exa for professional profiles and experts
  6. Always check: Use deep_researcher_check to monitor long-running research tasks

Rate Limits

Exa MCP has a generous free plan. For higher limits, add your own API key:

https://mcp.exa.ai/mcp?exaApiKey=YOUR_EXA_KEY

Get your key at: https://dashboard.exa.ai/api-keys

Integration Notes

This skill assumes Exa MCP is properly configured and available. The tools are accessed through MCP client integration and appear as available tools in your tool list.

More Information

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free