exa-research
Exa Research performs neural web search that understands meaning rather than keywords, offering four distinct actions: find relevant URLs by topic, get cited answers to factual questions, fetch full text from web pages, and discover similar sites. Each call costs $0.012, with content retrieval billed per URL.
Exa Research finds relevant URLs and web pages on any topic using semantic search that understands meaning, not just keywords.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
Exa Research finds relevant URLs and web pages on any topic using semantic search that understands meaning, not just keywords. Exa Research performs neural web search that understands meaning rather than keywords, offering four distinct actions: find relevant URLs by topic, get cited answers to factual questions, fetch full text from web pages, and discover similar sites. Each call costs $0.012, with content retrieval billed per URL.
Use it when
- Yes.
- Exa Research delivers factual answers grounded in real web sources with citations included.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
BlockRunAI/blockrun-mcp/exa-research · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is exa-research and how does neural web search for research work?
Exa Research performs neural web search that understands meaning rather than keywords, offering four distinct actions: find relevant URLs by topic, get cited answers to factual questions, fetch full text from web pages, and discover similar sites. Each call costs $0.012, with content retrieval billed per URL.
Can exa-research find academic papers online by topic?
Yes. Exa Research supports searching for and retrieving academic research papers by topic as one of its core intents. The skill uses semantic understanding to locate papers relevant to your research area, complementing its broader web search capabilities.
How does exa-research provide cited answers from web sources?
Exa Research delivers factual answers grounded in real web sources with citations included. When you ask a question, the skill retrieves relevant web pages and returns answers tied to those sources, ensuring transparency about where information comes from.
Can I use exa-research to discover competitor websites and similar pages?
Yes. Exa Research includes competitor discovery as a core capability, allowing you to find competitor websites and discover similar pages to any given URL. This helps identify related sites and understand your competitive landscape through semantic similarity.
Does exa-research support batch URL content extraction and fetching full text?
Yes. Exa Research can extract and fetch full text content from multiple URLs at once, enabling batch processing. This allows you to retrieve webpage text without needing a browser, with content retrieval billed per URL accessed.
What license does exa-research use?
Exa Research is released under the MIT license, allowing broad use and modification while maintaining attribution to the original creators.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Exa Research
Neural web search via BlockRun. Understands meaning, not keywords. Four distinct actions for different research modes.
How to Call from MCP
As of v0.14.1 the blockrun_exa tool is path-based. Pass the endpoint name as path and the request as body:
```ts blockrun_exa({ path: "search", body: { query: "AI agent frameworks 2026", numResults: 10 } }) blockrun_exa({ path: "answer", body: { query: "What is speculative decoding?" } }) blockrun_exa({ path: "contents", body: { urls: ["https://example.com/a", "https://example.com/b"] } }) blockrun_exa({ path: "find-similar", body: { url: "https://arxiv.org/abs/2401.12345", numResults: 5 }
(truncated - see the full file via the links below)
File tree — 1 file
skills/exa-research/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Find relevant URLs and web pages on a research topic using semantic meaning”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Web Research provides access to neural search and web scraping through x402-protected endpoints, combining Exa's semantic capabilities with Firecrawl's extraction power. Use it for deep investigations, finding similar content, extracting clean text from blocked sites, and crawling multiple pages—each with transparent per-task pricing starting at $0.002.
Query live odds and historical price data across Polymarket, Kalshi, Limitless, and other prediction venues through a single x402 gateway. Track smart-wallet positioning, leaderboards, and wallet P&L; retrieve candlesticks, orderbook snapshots, and volume charts that free APIs cannot provide. No account or API key required—pay only for what you call.
Exa Search performs broad web searches across blogs, news, research papers, and company sites with automatic content extraction. Query results return highlights, summaries, or full text alongside metadata like publication dates and authors. Use it when you need web-wide coverage beyond academic databases.
Exa Research provides Q&A capabilities with source attribution, combining the Answer API for cited responses with deep search for query expansion and summaries. Use it to build research automation, fact verification, and long-form reports with streaming support.
Exa-search combines keyword and semantic web retrieval for research-grade lookups on scientific and technical topics. Route queries to web search for topic research or URL extraction for fetching specific pages and academic PDFs. Use category filters and domain allowlists to prioritize peer-reviewed journals, preprints, and institutional sources.
This skill tackles research by decomposing topics into 3-5 key subtopics, then gathering and reasoning through factual information for each. It synthesizes findings into a coherent summary while flagging areas of uncertainty or debate, and suggests related questions worth exploring next.