Integration

Kagi Search API integration

Kagi Search API gives programmatic access to Kagi's ad-free premium web search: run a query and get ranked web results plus, depending on the query, news, images, videos, podcasts, code, direct answers, infoboxes, related searches and results from Kagi's own small-web and news indexes. Searches can be narrowed with lenses (sites, keywords, file type, date range, region), re-ranked with per-domain rules, and can fetch the full markdown of the top results in the same call. A second tool extracts the readable markdown content of up to ten web pages at once. The experimental markdown response format is not exposed (results always come back as JSON), and the v0 Universal Summarizer, FastGPT and enrichment routes are not part of this API. Authentication is an API key from the Kagi API dashboard, sent as a Bearer token in the Authorization header; usage is billed pay-per-use.

Connect Kagi Search API How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Kagi Search API.Built from the 2 Kagi Search API tools below, on the connection you add once.

What you can do with Kagi Search API

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.

Page content, 1 operation

extract_pagesExtract pagesPOSTFetches up to 10 HTTPS web pages concurrently and returns the readable content of each as markdown in data (url, markdown, or error when a page could not be extracted).

Search result, 1 operation

search_webSearch webPOSTRuns a Kagi web search, results grouped by type under data: data.search holds the web results (url, title, snippet, time, image), and lists such as news, image, video, direct_answer, infobox or related_search appear when the query calls for them.

Use Kagi Search API from Claude Code, Cursor or Codex

Connect Kagi Search API in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Kagi Search API 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 Kagi Search API

Create your workspace
Sign up free. Nothing to install.
Connect Kagi Search API once
Add your Kagi Search API 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.