exa-research

Search the web semantically and return cited sources via Exa API.

473|52|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/BlockRunAI/blockrun-mcp --skill exa-research-blockrunai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exa-research
Source: https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/exa-research
Command: npx skills add https://github.com/BlockRunAI/blockrun-mcp --skill exa-research-blockrunai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Neural web search often yields keyword-focused results without grounding. Exa Research enables semantic web search with grounded sources for reliable, citation-backed answers across products, papers, competitors, and web content.

Core Features & Use Cases

  • Semantic search over web pages, papers, and news with source citations
  • Answer with citations and a list of sources for grounding
  • Contents: fetch full text of URLs for context
  • Similar: discover related sites or competitors

Quick Start

Ask Exa Research to locate recent papers and credible sources about your topic and return a grounded, cited summary.

Frequently Asked Questions about exa-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find credible web sources with citations for academic research?

Semantic web search finds credible web sources and citations for academic research by applying neural search to locate relevant papers and content with grounded source URLs.

Can I fetch the full text of web pages after running a semantic search?

Yes, after running a semantic search you can fetch the full text contents of the discovered URLs to provide deeper context for your research queries and citation-backed summaries.

What's the best way to discover related sites or competitors for product research?

Use the find-similar functionality to discover related sites or competitors by locating web pages semantically similar to a known URL, delivering grounded results for competitive analysis.

Does semantic web search support category filtering for news and academic papers?

Semantic web search supports category filtering to narrow results across product research, academic literature, competitive analysis, and content discovery where semantic relevance matters.

How do I get grounded answers with a list of sources instead of keyword-focused results?

Use the answer API path to generate grounded answers with a list of sources, moving beyond keyword-focused results by applying neural search to return citation-backed responses.

What are the limitations of neural web search for content discovery?

Neural web search for content discovery requires clear cost models and category filtering to manage API usage, and relies on semantic relevance which may miss exact keyword matches.