AuraCite MCP
AuraCite measures how AI engines mention, cite, and recommend brands, with an evidence-grade methodology for German and international e-commerce teams.
What it can do
- List Brands: List all brands for a project
- Get Mentions: Get brand mentions across AI engines, newest first. Use `days` to limit to the last N days. For a date-scoped mention COUNT, read the total from get_dashboard_stats or get_ai_visibility_
- Get Citations: Get citations where the brand was cited in AI responses, newest first. Use `days` to limit to the last N days. For a date-scoped citation COUNT, read the total from get_dashboard_stats
What data it sees
Do you need an account
No: the server works without sign-in
AuraCite measures how AI engines mention, cite, and recommend brands, with an evidence-grade methodology for German and international e-commerce teams. This hosted MCP server exposes that data to any compatible agent: tracked brands, AI mentions, citations, share of voice, visibility score, competitors, trends, per-engine breakdowns, brand comparison, AI-crawler access, and Google Search Console performance (top queries, pages, country and device breakdowns). The server runs at https://auracite.de/mcp/rpc using Streamable HTTP (JSON-RPC 2.0). Authentication is OAuth 2.1 with PKCE S256 and dynamic client registration; an API-key header (Bearer or X-API-Key) works as fallback for CI and headless setups. Default access is read-only (mcp:read). Writes, provider scans, and admin actions are not available in the default scope. They require stronger scopes plus a server-side approval chain with hard credit caps and audit events.
How to connect
How to connect AuraCite MCP to Claude
The server address to paste into Claude settings:
https://auracite--m-g-alaeldin.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect AuraCite MCP to ChatGPT
The server address to paste into ChatGPT settings:
https://auracite--m-g-alaeldin.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect AuraCite MCP to Cursor
The server address to paste into Cursor settings:
https://auracite--m-g-alaeldin.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (35)
Raw names from tools/list. Only developers need these.
| list_brands | List all brands for a project |
| get_mentions | Get brand mentions across AI engines, newest first. Use `days` to limit to the last N days. For a date-scoped mention COUNT, read the total from get_dashboard_stats or get_ai_visibility_overview rather than counting these rows. |
| get_citations | Get citations where the brand was cited in AI responses, newest first. Use `days` to limit to the last N days. For a date-scoped citation COUNT, read the total from get_dashboard_stats or get_ai_visibility_overview rather than counting these rows. |
| list_prompts | List all tracked GEO prompts for a project |
| get_dashboard_stats | Get dashboard statistics (mentions, citations, sentiment) for a project |
| get_crawler_hits | Get AI-crawler access analytics for the project (the INPUT side of AI visibility): KPI summary, per-crawler breakdown, most-crawled pages, and crawl→citation funnel gaps (pages AI bots fetch heavily but rarely cite). Answers 'which pages does GPTBot crawl most?'. Read-only. |
| get_gsc_search_analytics | Get Google Search Console search-analytics rows (per query+page): clicks, impressions, CTR, and average Google position over a day window (page ~ position/10). Read-only. |
| get_gsc_top_queries | Get the tenant's top Google Search queries aggregated over a day window (summed clicks/impressions, impression-weighted CTR and average position). Read-only. |
| get_gsc_breakdown | Get the tenant's Google Search performance broken down by country or device over a day window (clicks, impressions, CTR, average position). Read-only. |
| get_gsc_top_pages | Get the tenant's top Google Search pages (URLs) aggregated over a day window (clicks, impressions, CTR, average position). Read-only. |
| get_gsc_trend | Compare top Google queries between the current window and the preceding window of equal length (click/impression/position deltas; position_delta<0 = improved). Read-only. |
| get_ai_visibility_overview | Unified cross-source AI-visibility snapshot: Google Search (GSC top queries+pages), AI-crawler access + crawl→citation gaps, and AI-engine mentions/citations — in one call. Read-only. |
| get_intelligence_overview | Read-only Visibility Intelligence overview for the API-key-bound project, including source health, opportunities, and outcome-loop state |
| get_intelligence_freshness | Read-only freshness summary for Visibility Intelligence sources, including stale or missing refresh candidates |
| list_intelligence_refresh_candidates | List stale, missing, or low-quality Visibility Intelligence sources that should be refreshed or refilled; read-only |
| create_intelligence_refresh_plan_draft | Create a read-only Intelligence refresh plan draft for human/operator review; no source sync, provider call, credit spend, or mutation is performed |
| get_intelligence_refresh_status | Read-only status snapshot for the Intelligence refresh loop, including freshness, candidate counts, and safe next action |
| list_intelligence_opportunity_briefs | List compact Visibility Intelligence opportunity briefs with measurement and handoff state |
| get_intelligence_opportunity_brief | Get one evidence-backed Visibility Intelligence opportunity brief |
| list_action_handoffs | List persisted Action Center handoff and outcome-reconciliation state derived from Visibility Intelligence opportunities |
| get_vault_next_actions | Read secret-safe, curated project-memory next actions for Agent Hub planning |
| get_project_status | Read secret-safe, curated project status for Agent Hub handoffs |
| get_recent_changelog | Read secret-safe, curated recent project changelog for Agent Hub handoffs |
| get_agent_hub_timeline | Read a compact, secret-safe Agent Hub timeline combining current state, recent changelog, next actions, and recommended next step |
| list_project_memory_entries | Read recent server-side Agent Hub project-memory entries; raw Vault files and secrets are not exposed |
| create_context_pack_draft | Create a read-only context pack draft for a Visibility Intelligence opportunity; no mutation, provider call, or credit spend is performed |
| create_action_handoff_draft | Create a draft Action Center handoff payload for human review; the draft is not promoted or persisted |
| write_approval_note_draft | Write a human approval note draft for a Visibility Intelligence handoff; approval and promotion remain separate steps |
| list_competitors | List detected competitor brands for a project |
| get_visibility_score | Compute a composite GEO visibility score (0–100) with letter grade |
| get_share_of_voice | Get share-of-voice percentage across AI engines for a project |
| get_trend_data | Get time-series trend data for mentions, citations, and sentiment |
| get_ai_engine_breakdown | Break down AI engine usage (ChatGPT, Gemini, Perplexity, etc.) for a project |
| compare_brands | Compare two brands' AI visibility side-by-side |
| list_projects | List all projects in your tenant. Each project tracks one client/brand; use the returned project_id with project-scoped tools. |