Integration

Tavily integration

Tavily is an AI-powered search engine API designed specifically for AI agents and applications. It provides real-time, accurate search results optimized for LLMs, including web search, news search, content extraction, website crawling, URL mapping, and deep research. Perfect for building AI assistants, research tools, and applications requiring up-to-date web information.

Connect Tavily How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Tavily.Built from the 7 Tavily tools below, on the connection you add once.

Common Tavily use cases

billing review
market research
content extraction
research assistant
sitemap generation
monitoring API consumption
website content extraction
organization usage reporting
fact checking
URL inventory

What you can do with Tavily

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Content, 3 operations

crawlCrawlPOSTCrawls a website from a root URL, following links to discover and extract content from multiple pages.
extractExtractPOSTExtracts and parses content from URLs. Returns clean text and metadata.
mapMapPOSTMaps a website's URL structure by discovering all linked pages from a root URL.

Usage, 2 operations

get_organization_usageGet organization usagePOSTRetrieves organization-wide Tavily usage across API keys.
get_usageGet usageGETRetrieves API key usage details including credit consumption and remaining balance.

Research, 1 operation

researchResearchPOSTPerforms deep web research on a topic, returning a comprehensive report with citations.

Search, 1 operation

searchSearchPOSTAI-powered web search optimized for LLMs. Returns relevant results with content snippets.

Tavily API rate limits

Official default limits are 100 RPM for development keys and 1000 RPM for production keys. Crawl has a separate 100 RPM limit for both environments; research task creation has a separate 20 RPM limit for both environments; usage has a separate 10 requests per 10 minutes limit for both environments.

These are the limits Tavily documents, not ones LiveContext measured. They can change and often depend on your plan, so check the Tavily documentation for current values.

Use Tavily from Claude Code, Cursor or Codex

Connect Tavily in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Tavily operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Tavily

Create your workspace
Sign up free. Nothing to install.
Connect Tavily once
Add your Tavily connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Tavily integration FAQ

What can you do with the Tavily integration?

LiveContext exposes 7 operations on Tavily, covering content, usage, research and search. Common uses include billing review, market research and content extraction.

What are the Tavily API rate limits?