Exa Search
Wire Exa neural search into your agent so you can pull live web pages, code context, and company intel without leaving Claude Code.
Overview
Exa Search is an agent skill most often used in Idea (also Validate, Build) that runs neural web and code-context retrieval through the Exa MCP server.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill exa-searchWhat is this skill?
- Neural web search via Exa MCP (`web_search_exa`) for news, docs, and general references
- Code-focused retrieval via `get_code_context_exa` for API examples and technical snippets
- Documented npx `exa-mcp-server` setup with `EXA_API_KEY` in `~/.claude.json`
- Covers company, competitor, people, and deep research prompts tied to dev tasks
- Skill explicitly flags drift risk—tool names and limits must be verified against current Exa docs
- Documents 2 core Exa MCP tools: web_search_exa and get_code_context_exa
Adoption & trust: 4.2k installs on skills.sh; 210k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need trustworthy, up-to-date web and code references during an agent session but cannot rely on the model’s static knowledge or ad-hoc scraping.
Who is it for?
Solo builders who already use MCP in Claude Code and want faster research loops for markets, APIs, and technical references.
Skip if: Offline-only workflows, air-gapped environments, or teams unwilling to provision and pay for an Exa API key and network access.
When should I use this skill?
User needs web search, code examples, company intel, people lookup, or says search for, look up, find, or what's the latest on.
What do I get? / Deliverables
Your agent calls Exa MCP tools and returns grounded search results and code context you can cite while scoping, designing, or implementing features.
- Web search result summaries
- Code context excerpts for implementation
- Research notes grounded in retrieved sources
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Discovery and background research are the first place solo builders need authoritative, current sources before they commit to scope or implementation. Research subphase is the canonical shelf for search-and-gather workflows that feed competitor, market, and technical fact-finding.
Where it fits
Pull current positioning and product pages for adjacent tools before you narrow your niche.
Verify whether a proposed integration or pricing model still matches what vendors publish today.
Fetch fresh API docs and code snippets while wiring a third-party service into your app.
How it compares
Use as a dedicated neural-search MCP integration instead of vague “search the web” prompts without a configured retrieval server.
Common Questions / FAQ
Who is exa-search for?
Indie and solo developers using Claude Code, Cursor, or similar agents who need live web, code, and company research during product work.
When should I use exa-search?
During Idea research for competitors and markets, Validate when checking pricing or landscape claims, and Build when hunting API docs, examples, or technical references—or whenever the user says search, look up, or find.
Is exa-search safe to install?
It requires network access, shell via npx, and a third-party API key; review the Security Audits panel on this page and Exa’s data policies before storing keys in local config.
SKILL.md
READMESKILL.md - Exa Search
# Exa Search > **Drift-prone skill.** Exa MCP tool names, parameters, and account limits can > change. Confirm the exposed tool surface and current Exa docs before relying > on a specific search mode, category, or livecrawl behavior. Neural search for web content, code, companies, and people via the Exa MCP server. ## When to Activate - User needs current web information or news - Searching for code examples, API docs, or technical references - Researching companies, competitors, or market players - Finding professional profiles or people in a domain - Running background research for any development task - User says "search for", "look up", "find", or "what's the latest on" ## MCP Requirement Exa MCP server must be configured. Add to `~/.claude.json`: ```json "exa-web-search": { "command": "npx", "args": ["-y", "exa-mcp-server"], "env": { "EXA_API_KEY": "YOUR_EXA_API_KEY_HERE" } } ``` Get an API key at [exa.ai](https://exa.ai). This repo's current Exa setup documents the tool surface exposed here: `web_search_exa` and `get_code_context_exa`. If your Exa server exposes additional tools, verify their exact names before depending on them in docs or prompts. ## Core Tools ### web_search_exa General web search for current information, news, or facts. ``` web_search_exa(query: "latest AI developments 2026", numResults: 5) ``` **Parameters:** | Param | Type | Default | Notes | |-------|------|---------|-------| | `query` | string | required | Search query | | `numResults` | number | 8 | Number of results | | `type` | string | `auto` | Search mode | | `livecrawl` | string | `fallback` | Prefer live crawling when needed | | `category` | string | none | Optional focus such as `company` or `research paper` | ### get_code_context_exa Find code examples and documentation from GitHub, Stack Overflow, and docs sites. ``` get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000) ``` **Parameters:** | Param | Type | Default | Notes | |-------|------|---------|-------| | `query` | string | required | Code or API search query | | `tokensNum` | number | 5000 | Content tokens (1000-50000) | ## Usage Patterns ### Quick Lookup ``` web_search_exa(query: "Node.js 22 new features", numResults: 3) ``` ### Code Research ``` get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000) ``` ### Company or People Research ``` web_search_exa(query: "Vercel funding valuation 2026", numResults: 3, category: "company") web_search_exa(query: "site:linkedin.com/in AI safety researchers Anthropic", numResults: 5) ``` ### Technical Deep Dive ``` web_search_exa(query: "WebAssembly component model status and adoption", numResults: 5) get_code_context_exa(query: "WebAssembly component model examples", tokensNum: 4000) ``` ## Tips - Use `web_search_exa` for current information, company lookups, and broad discovery - Use search operators like `site:`, quoted phrases, and `intitle:` to narrow results - Lower `tokensNum` (1000-2000) for focused code snippets, higher (5000+) for comprehensive context - Use `get_code_context_exa` when you need API usage or code examples rather than general web pages ## Related Skills - `deep-research` — Full research workflow using firecrawl + exa together - `market-research` — Business-oriented research with decision frameworks