Exa
The search engine built for AIs — semantic web search, page contents, Websets, and research APIs, plus a hosted MCP server.
Exa is a search engine built for AI consumers, not human browsers: a semantic Search API with deep-search profiles, a Contents API returning clean text and summaries, Websets for enriched entity sets, and Exa Agent for research. Its hosted MCP server (mcp.exa.ai/mcp) works keyless on a rate-limited free tier.
Exa is what search looks like when the customer is an agent: semantic search in, clean text out. Where Google optimizes for a human scanning ten blue links, Exa's Search API returns machine-ranked results and its Contents API hands back the page as clean text, highlights, or AI summaries — the retrieval layer for agents and RAG pipelines, sold as an API.
Highlights
- Search built for LLM consumption — neural/semantic search with speed/quality profiles up to Deep Search and deep-reasoning modes for research-grade queries.
- Contents, not links — clean page text, highlights, and summaries per result; structured outputs via an
outputSchemaparameter. - Websets — build and enrich entity sets ("every Series-B devtools company and their CTOs") as a product, not a scraping project.
- Research & Monitors — multi-step research runs (Exa Agent, launched June 2026) and standing watches on a query, exposed as API products.
- Hosted search MCP server — at
mcp.exa.ai/mcp, MIT-licensed, with keyless rate-limited access for instant trial.
In an AI-assisted workflow
claude mcp add --transport http exa https://mcp.exa.ai/mcp
# keyless works (rate-limited); add x-api-key from dashboard.exa.ai for real use
# then:
# > Research how teams are handling MCP server auth in production —
# > search broadly, fetch the three best sources, and synthesizeThe MCP toolset is deliberately small after a 2025–26 consolidation: web_search_exa and web_fetch_exa by default, plus opt-in advanced-search (web_search_advanced_exa) and Exa Agent (agent_run) tools. (Older tutorials referencing linkedin_search_exa or deep_researcher_* tools are out of date — Exa deprecated them in favor of web_search_advanced_exa and its since-retired Research API, and multi-step research in MCP now runs through agent_run.)
TIP
Exa pairs with Firecrawl as the two halves of agent web-data: Exa finds the right pages; Firecrawl extracts at depth and scale from sites you already know. Plenty of agent stacks run both.
Good to know
Exa Labs raised a $250M Series C at a $2.2B valuation (led by a16z, announced May 2026) — the "search engine for AIs" thesis is well-funded and the API surface is moving fast. Pricing, as of September 2026 from exa.ai/pricing: $20 in free credits at signup plus $10 more every month, then metered pay-as-you-go — $7 per 1,000 searches, $1 per 1,000 pages per content type, $12–$15 per 1,000 deep-search requests — with enterprise adding volume discounts and zero-data-retention. Like any web-content tool, what it fetches enters your agent's context — treat retrieved pages as untrusted input in injection-sensitive setups.
Frequently asked questions
- What makes Exa different from a normal search API?
- It's built for machines doing retrieval, not people browsing: neural/semantic search over the web with relevance tuned for LLM consumption, a Contents API that returns clean text, highlights, and summaries instead of links to render, structured outputs via output schemas, and deep-search profiles that trade latency for quality when an agent is researching rather than skimming.
- How do I add Exa to Claude Code?
- One verified command: claude mcp add --transport http exa https://mcp.exa.ai/mcp. It even works keyless with rate limits; add an API key from dashboard.exa.ai (x-api-key header) to lift them. The server exposes web_search_exa and web_fetch_exa by default, plus opt-in web_search_advanced_exa and agent_run tools.
- Is Exa free?
- Freemium and pay-as-you-go, with no subscription tier. As of September 2026, exa.ai/pricing gives new accounts $20 in free credits and adds $10 in free credits every month, then meters by product: $7 per 1,000 searches, $1 per 1,000 pages per content type, $12 per 1,000 deep-search requests ($15 for deep-reasoning), and $5 per 1,000 answers. Enterprise adds volume pricing and zero-data-retention. The MCP server itself is MIT-licensed.
Filed under
search · web-data · mcp · api · agents
Related
- FirecrawlThe API to search, scrape, and crawl the web for AI — clean Markdown out of any site, LLM-powered extraction, and a first-class MCP server.
- The Best MCP Servers in 2026The MCP servers actually worth connecting in 2026 — Context7, GitHub, Chrome DevTools, Playwright, Serena, Exa, Firecrawl, and official vendor servers.
- Adding MCP Servers to Claude Code: Local, Remote, and Project-ScopedThe complete claude mcp add reference — stdio vs HTTP transports, local/project/user scopes, .mcp.json with env expansion, OAuth via /mcp, and the gotchas.
- Agent Tool Integration EngineerUse this agent to wire tools and function-calling into an agent loop reliably — clean tool schemas, errors fed back as observations, retries with limits, idempotency, and parallel calls. Examples — "connect our APIs as agent tools", "our agent calls tools wrong / ignores tool errors", "add function-calling with proper error recovery to our agent".
- Data ScientistUse this agent for data analysis — exploration, statistics, SQL, and clear findings. Examples — analyzing a dataset, writing an analytical SQL query, summarizing experiment results.
- How RAG Actually Works: Ingestion, Chunking, Retrieval & RerankingA clear, practical walkthrough of the retrieval-augmented generation pipeline — what each stage does, where it fails, and how the pieces fit together.
- TavilyThe web-access layer for agents — Search, Extract, Crawl, Map, and Research APIs purpose-built for LLMs, behind one key, with a hosted MCP server.
- Brave Search APIBrave's web search API on its own independent index: ranked results, LLM Context grounding chunks, and cited answers from an OpenAI-compatible endpoint.