Exa Web Search V2

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API ke...

Security Scan

The skill's requests and runtime instructions are internally consistent with a web/code/company search integration that uses the mcporter CLI to call Exa's MCP endpoints, but it will send your queries to an external service and the package metadata has minor inconsistencies you may want to confirm.

Purpose & Capability

The skill is an instruction-only wrapper for calling Exa MCP via the mcporter binary. Requiring mcporter is expected given the documented mcporter call commands and the skill's search purpose.

Instruction Scope

SKILL.md only instructs the agent to run mcporter commands (list, config add, call). These commands will add a persistent mcporter config entry and send query text to the external endpoint (https://mcp.exa.ai/mcp). There are no instructions to read arbitrary local files or other credentials, but user queries (possibly containing sensitive info) will be transmitted to a third-party service.

Install Mechanism

There is no install spec and no code files; the skill expects an existing mcporter binary. This is low-risk from an installer perspective, but the binary itself (mcporter) is an external dependency you must trust.

Credentials

The skill does not request environment variables, credentials, or config paths. That is proportionate to its stated purpose. However, mcporter config changes are required to register the MCP endpoint.

Persistence & Privilege

The skill does not request always:true and is user-invocable only. It does instruct adding a persistent mcporter config entry (mcporter config add), which modifies the user's mcporter configuration but not platform-wide settings or other skills.

Assessment

This skill is coherent: it calls Exa's MCP through the mcporter CLI. Before installing or using it, confirm you trust the mcporter binary and the Exa MCP endpoint (https://mcp.exa.ai). Be aware that any queries you send (including code, company names, or prompts) will be transmitted to that external service and the mcporter config command will add a persistent entry to your mcporter config. Also note a minor metadata mismatch in the packaged files (different slug/version/ownerId than registry metadata) — you may want to verify the publisher or prefer an official release (GitHub/npm links are provided) before proceeding. Avoid sending secrets or sensitive internal documents to the skill until you are confident in the service's privacy/security posture.

Exa Web Search (Free)

Neural search for web, code, and company research. No API key required.

Setup

Verify mcporter is configured:

mcporter list exa

If not listed:

mcporter config add exa https://mcp.exa.ai/mcp

Core Tools

web_search_exa

Search web for current info, news, or facts.

mcporter call 'exa.web_search_exa(query: "latest AI news 2026", numResults: 5)'

Parameters:

• query - Search query
• numResults (optional, default: 8)
• type (optional) - "auto", "fast", or "deep"

get_code_context_exa

Find code examples and docs from GitHub, Stack Overflow.

mcporter call 'exa.get_code_context_exa(query: "React hooks examples", tokensNum: 3000)'

Parameters:

• query - Code/API search query
• tokensNum (optional, default: 5000) - Range: 1000-50000

company_research_exa

Research companies for business info and news.

mcporter call 'exa.company_research_exa(companyName: "Anthropic", numResults: 3)'

Parameters:

• companyName - Company name
• numResults (optional, default: 5)

Advanced Tools (Optional)

Six additional tools available by updating config URL:

• web_search_advanced_exa - Domain/date filters
• deep_search_exa - Query expansion
• crawling_exa - Full page extraction
• people_search_exa - Professional profiles
• deep_researcher_start/check - AI research agent

Enable all tools:

mcporter config add exa-full "https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"

# Then use:
mcporter call 'exa-full.deep_search_exa(query: "AI safety research")'

Tips

• Web: Use type: "fast" for quick lookup, "deep" for thorough research
• Code: Lower tokensNum (1000-2000) for focused, higher (5000+) for comprehensive
• See examples.md for more patterns

Resources

• GitHub
• npm
• Docs