Exa Connector for AI agents.
10 live capabilities
Find conceptually relevant web content for deep research and competitive analysis.
Waiting for input…
Why people use Exa
Exa Semantic Search for Research Efficiency
With this Connector, your agent does the heavy lifting. It can search the web for conceptual matches and pull clean text from multiple URLs in one go. You get a structured summary of the web instead of a pile of open tabs.
What Vinkius changes
Your agent gets a way to understand the web like a human does.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding research papers on niche AI topics
A researcher asks for papers on 'memory infrastructure for agents' and gets papers that match the concept, even if they don't use that exact phrase.
- Real-world use case 02
Competitor discovery
A content strategist points the agent at a competitor's blog and asks for similar sites to see who else is in the space.
- Real-world use case 03
Building a knowledge base
A user provides 20 URLs and asks the agent to extract the main highlights from all of them to create a summary.
Complete set · 10capabilities
The complete Exa capability set.
These are the exact actions your AI can choose when you ask it to work with Exa.
01—04
4 capabilities in this set.
Part of 10 available through Exa.
- 01 Capability
Answer
Get an AI answer
- 02 Capability
Find similar
Great for competitive analysis and research. Find similar pages
- 03 Capability
Find similar with contents
Find similar pages with content
- 04 Capability
Get contents
Extract page contents
05—07
3 capabilities in this set.
Part of 10 available through Exa.
- 05 Capability
Search domain
Useful for site-specific research or documentation lookups. Search within a domain
- 06 Capability
Search keyword
Traditional keyword search
- 07 Capability
Search neural
Ideal for conceptual queries and research topics. Neural semantic search
08—10
3 capabilities in this set.
Part of 10 available through Exa.
- 08 Capability
Search recent
Ideal for news and trending topics. Search recent content
- 09 Capability
Search
Returns titles, URLs, and relevance scores for matching pages. Search the web with AI
- 10 Capability
Search with contents
Search and extract page content
Set up in minutes
One URL. Then ask Exa to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Exa from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Exa, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Exa for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Exa URL.
- Step 03
Save and start
Save the connection and enable Exa in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"exa": {
"url": "https://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Exa
Open Agent mode in chat and ask: "Using Exa, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"exa": {
"url": "https://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Exa
Ask Copilot: "Using Exa, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"exa": {
"url": "https://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Exa
Open Cascade and ask: "Using Exa, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"exa": {
"url": "https://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Exa
Ask Cline: "Using Exa, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add exa --transport http "https://edge.vinkius.com/vk_preview_yX0o3kbQylbPvraZb07fJ4pytT29vYl6Z1kPSXHZ/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Exa
Ask Claude: "Using Exa, show me...". 10 tools are ready
Where the request belongs
Work Exa can move forward.
This is for the research analyst who is tired of digging through pages of irrelevant search results, or the AI developer building an agent that needs to browse the web with actual context.
AI Agent Developer
Builds agents that need to browse the web and understand context instead of just matching keywords.
Research Analyst
Finds deep connections between research papers and articles without getting lost in irrelevant results.
Content Strategist
Discovers competitors and related content at scale by finding pages that match the meaning of target URLs.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsExa
Find exactly the web content you need with semantic search that understands context and returns high-quality curated results.
Exa AI
Search the web with neural embeddings that understand meaning, not just keywords, and return the most relevant results for any query.
Jina AI
Search and read the web for AI. audit search results and reader content via AI.
Tavily
Search the web for AI. audit search context, answers, and extracted content via AI.
Linkup (AI Search & RAG)
Power your AI agents with real-time web search via Linkup. execute semantic queries and extract RAG-ready content.
Vertex AI Search
Search across your enterprise data using Google's semantic search and generative AI grounding.
Bring your own AI
Change the model, client or framework. Keep Exa connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Exa.
The practical details behind the request, access and result.
How does Exa help my AI agent search the web?
Exa gives your agent a way to understand the meaning behind your questions. Instead of just looking for keywords, it finds content that actually matches the concept of what you're looking for.
Can I use Exa to find competitors for my business?
Yes, you can point your agent at a competitor's website and ask it to find similar pages. This helps you discover related services and content across the web.
What is the difference between Exa and a standard search?
Standard search looks for exact word matches. Exa uses semantic understanding to find results that are relevant to your intent, even if they don't use your specific words.
How do I get clean text from multiple URLs at once?
You can provide a list of links to the agent, and it will use the extraction capabilities to pull out the relevant text and highlights into a structured format for you.
Can Exa find research papers that don't have specific keywords?
Yes, that is one of its primary strengths. Because it understands concepts, it can find relevant research papers based on the subject matter rather than just specific terminology.
Is Exa good for building a knowledge base?
It is excellent for this. You can use it to gather clean text and highlights from a curated list of sources to build a structured knowledge base for your agent.
How is Exa different from Google Search?
Exa uses neural embedding models to understand the meaning of your query, not just keywords. When you search 'startups building AI infrastructure', Google returns pages containing those exact words. Exa returns companies that match that concept. even if their pages use completely different terminology. It also provides specialized search indexes for people, companies, code, and academic papers.
What does the free tier include?
Exa's free tier includes 1,000 searches per month with content extraction included for up to 10 results per search at no additional cost. No credit card required. For higher volumes, paid plans offer increased quotas and priority support.
Can I filter results by domain, date, or category?
Yes! Exa supports powerful filtering options: include/exclude specific domains, filter by publication date range, search within specific categories (news, blog, academic, etc.), and even use domain path filtering to search within specific sections of a website.
Can I perform a meaning-based search instead of keywords via AI?
Yes! Use the search capability. Provide your query and enable useAutoprompt. Exa will use its neural embeddings to find links that match the intent of your question.
How do I find articles similar to a specific URL?
Use the find_similar capability. Provide the seed URL, and the agent will retrieve a list of pages that are semantically related to that content.
Is it possible to extract cleaned text from multiple pages via AI?
Absolutely. Use the get_contents query. Provide an array of URLs or Exa IDs, and the agent will return the cleaned text content and metadata for each page.
One connection away
Give your agent a direct line to Exa.
Connect Exa once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available