AnswerixAI Docs AnswerixAI Docs AI Search Visibility, GEO & AEO platform

MCP server

Connect Claude Desktop, Claude Code, Cursor, Zed, and any MCP-aware client to your AnswerixAI data — zero install.

On this page 9

AnswerixAI ships a Model Context Protocol server at /api/mcp on your AnswerixAI host so AI assistants can query your brand visibility data through natural-language conversation. No npm package, no local process — just a URL and an API key.

Generate an API key

  1. Open your AnswerixAI dashboard → SettingsAPI Keys
  2. Click New key, give it a memorable name (e.g. Claude — laptop)
  3. Copy the token (it starts with ans_). It's shown once — store it in your password manager

Connect Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{
  "mcpServers": {
    "answerix": {
      "url": "https://your-answerix-host/api/mcp",
      "headers": {
        "Authorization": "Bearer ans_..."
      }
    }
  }
}

Restart Claude Desktop. Type "List my AnswerixAI brands" — Claude should call the list_brands tool and show your brands inline.

Connect Claude Code

bash
claude mcp add answerix --transport http https://your-answerix-host/api/mcp \
  --header "Authorization: Bearer ans_..."

Self-host? Point at your own instance

The MCP endpoint lives at /api/mcp on whatever host runs the AnswerixAI app. If you self-host at answerix.mycompany.internal, use that base URL instead.

Available tools

Tool What it does
list_brands List brands the authenticated user can access.
get_visibility_summary Aggregate visibility score, mentions, citations, top competitors for a brand over an optional date range / model / region.
get_visibility_trend Day-by-day visibility series for charting movement over time.
list_topics List the topics on a brand with a prompt count per topic. Use for coverage audits (empty / over-concentrated topics).
list_prompts List the prompts tracked on a brand, optionally filtered by topic, active status, or capped via limit.
get_prompt_performance Per-prompt visibility with platform breakdown.
get_prompt_volumes Estimated AI search volumes for tracked prompts.
list_citations The URLs AI engines cite alongside the brand, with source-type classification.
get_competitor_comparison Side-by-side visibility vs. named competitors.
get_ai_traffic Real visits arriving from AI answer engines (pixel data).
list_content_opportunities / get_content_opportunity Content gaps ranked by opportunity score.
generate_content_brief Generate (or fetch the cached) structured editorial brief for an opportunity.
update_opportunity_status Move an opportunity between new / sent / in_progress / done / dismissed.
list_shopping_cards / get_product_visibility Product card presence in shopping-style AI answers.
run_site_audit / list_site_audits / get_site_audit / get_site_audit_quota Trigger and inspect AI-readability site audits.

Try it

Ask your client things like:

  • "List my AnswerixAI brands."
  • "What's my visibility score on ChatGPT for the last 7 days?"
  • "Are my topics balanced?" / "Which topic has the most prompts?"
  • "Show me the prompts in my pricing topic."
  • "Who are my top 5 competitors by mention count this month?"
  • "Run a site audit on my primary domain and summarize the weakest category."

The model picks the right tool, fills in the brand id and filters, and answers in plain English using the returned data.

REST mirrors

Every MCP tool is also exposed as a plain REST endpoint under /api/mcp/* (e.g. GET /api/mcp/brands, GET /api/mcp/visibility-summary?brand_id=…) using the same ans_ bearer key — handy for scripts and integrations that don't speak MCP. See the API reference.

Revoking access

If a key leaks or you stop using a client, open Settings → API Keys and click the trash icon. Clients using that key lose access immediately.

Transport

The server speaks the MCP Streamable HTTP transport in stateless mode — every request is self-contained, no session state is kept between calls. This makes it work cleanly behind any HTTP load balancer.