Integration

Dappier integration

Dappier serves real-time data to AI agents through AI models and data models listed on its marketplace. Ask a Dappier AI model a question (live web search, breaking news, stock prices, sports, weather and more) and get a generated answer, or get article recommendations from a data model by query or URL with a choice of search algorithm. Publishers and advertisers can also read their Ask AI widget analytics, the raw Ask AI conversation logs (end-user prompts and answers), sponsored conversation campaign analytics and session intelligence. Left out: the ZeroClick variants of search and recommendations, which are authenticated by an HMAC signature over each request. Authentication is a Dappier API key (it starts with ak_) created on the platform's API keys page, sent as a Bearer token.

Connect Dappier How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Dappier.Built from the 6 Dappier tools below, on the connection you add once.

What you can do with Dappier

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.

Aimodel, 1 operation

query_ai_modelQuery ai modelPOSTSends a natural-language question to a Dappier AI model and returns its generated answer as text in message. The model decides the data source: live web search, news, weather, stock and financial data, and more.

Ask ai, 1 operation

get_ask_ai_analyticsGet ask ai analyticsGETReturns Ask AI widget engagement for a date window (the last 7 days by default): widget loads, viewable sessions, queries, clicks, rates and session time, plus a daily breakdown. Filters by widget, placement, deployment type or ad ids.

Log, 1 operation

list_ask_ai_logsList ask ai logsGETLists Ask AI conversation rows, newest first, for a date window (the last 7 days by default): each user prompt and AI answer in full, with widget, placement, page URL and time. Prompts can contain end users' personal data. Paginated.

Search, 1 operation

get_ai_recommendationsGet ai recommendationsPOSTReturns article recommendations from a Dappier data model for a query, keyword or page URL: title, summary, author, site, publication date, image and links, ranked by the chosen search algorithm (semantic by default).

Session intelligence, 1 operation

get_session_intelligenceGet session intelligenceGETReturns how end users use the account's Ask AI widgets over a date window (the last 7 days by default): engaged sessions, engagement time, intent breakdown, the text of the 10 most asked prompts, content category mix and query-depth distribution.

Use Dappier from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Dappier once
Add your Dappier 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.