Integration

Heeb LLM Mentions integration

Heeb measures how a brand shows up inside AI answers. An agent can ask one buyer-style question to several AI models at once (OpenAI, Anthropic Claude, xAI Grok, Perplexity and Google AI Mode) for a brand and a country, then read each model's answer, the sources and citations it used, the brands it ranked, whether the tracked brand was mentioned and with what sentiment, plus aggregate visibility (0 to 100) and sentiment (-1 to 1) scores. A query is a background job: submit it, then read its result. Every query is billed in prepaid Heeb credits, per model asked. Heeb publishes only these two routes; the credit balance is shown in the Heeb dashboard only. Authentication is an API key created on the API Keys page of the Heeb dashboard, sent in the x-api-key header.

Connect Heeb LLM Mentions How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Heeb LLM Mentions.Built from the 2 Heeb LLM Mentions tools below, on the connection you add once.

What you can do with Heeb LLM Mentions

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

get_query_resultGet query resultGETAgents: ask firstReads a query job: status is pending while models still answer (call again in about 30 seconds), else per-model answers, sources, citations, ranked mentions and sentiment, with visibility (0-100) and sentiment (-1 to 1) scores.
submit_querySubmit queryPOSTAgents: ask firstBilled: asks each listed model the prompt and checks how the entity appears. Returns a job_id at once; pass it to get_query_result, which answers status pending until the job ends (usually 30 seconds to 2 minutes).

Use Heeb LLM Mentions from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Heeb LLM Mentions once
Add your Heeb LLM Mentions 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.