Bring Ayzeo Into Your AI Assistant

MCP (Model Context Protocol) is the open standard for connecting AI assistants to external tools and data. Instead of an AI assistant being a sealed conversation, MCP lets it call real tools -- like querying your GSC data or generating a content page. Ayzeo's MCP server exposes your GEO data layer to any MCP-capable AI client so you can use Ayzeo from inside Claude Desktop, Cursor, Gemini CLI, or the OpenAI Responses API instead of context-switching to the dashboard.

Any client that supports Streamable HTTP remote MCP servers with a custom Authorization header. Verified today: Claude Code CLI (claude mcp add), Cursor (~/.cursor/mcp.json), Windsurf, Claude Desktop via the mcp-remote stdio bridge (Claude Desktop's native Custom Connector UI only supports OAuth client id/secret, not bearer tokens — so mcp-remote is the Ayzeo path there), Gemini CLI (httpUrl + headers), and the OpenAI Responses API / Agents SDK for programmatic agents. ChatGPT.com end-user app currently restricts custom MCP servers to a Developer-mode beta, so the reliable ChatGPT path today is the Responses API.

Fourteen tools in v1: get_project_info, get_analysis_results, run_website_analysis, get_citation_history, run_ai_visibility_check, get_project_stats, list_prompts, run_prompt, get_content_pages, get_brand_mentions, get_gsc_opportunities, get_gsc_queries, get_ga_ai_traffic, and create_content_page_from_query. The AI assistant discovers these automatically via the standard MCP tools/list handshake.

Pro and Enterprise plans. Free and Starter plans do not have access. Pro subscribers can create a project API token in project settings, paste the URL + token into their AI client, and start using it immediately -- the same token powers both the WordPress API and MCP.

Yes. Each token is scoped to a single project, but every MCP client (Claude Code, Cursor, Claude Desktop, Gemini CLI, etc.) lets you register multiple MCP servers in its config. Create one token per project, add each as a separate entry with a distinct name -- ayzeo-brand-a, ayzeo-brand-b, ayzeo-agency-client-3 -- and your assistant can reach all of them side by side. A dedicated organisation-scoped token is on the roadmap for agencies managing many projects, but the multi-entry workaround works today.

The MCP server reuses Ayzeo's existing ProjectApiToken authentication. Each token is scoped to a single project and carries the project owner's subscription. Rate limits are shared with the WordPress API (100 requests per 5 minutes per token). Tokens can be revoked at any time from project settings, which immediately cuts off any AI client using them.

ACOS (Ayzeo Content Opportunity Score) is a 0-100 composite score combining 9 weighted dimensions -- striking distance, CTR gap, impression volume, 30-day momentum, position trend, content gap, brand filter, long-tail classification, and traffic uplift -- to rank which GSC queries deserve a new content page. The get_gsc_opportunities MCP tool returns top-scoring queries with the full dimension breakdown plus weights, so the AI assistant can articulate exactly why a query is a good opportunity rather than just handing back a number.

Yes. The create_content_page_from_query tool triggers Ayzeo's content generation pipeline for a given query and returns the new page id plus generated SEO elements and edit URL. It counts against the standard 5-per-day content-page quota per project and requires an active paid subscription. In practice, an AI assistant will typically chain get_gsc_opportunities -> get_ga_ai_traffic -> create_content_page_from_query to close the full gap-to-draft loop.

Tools that depend on those integrations return a structured error with codes like gsc_not_connected, gsc_sync_pending, ga_not_connected, or ga_sync_pending -- along with a setupUrl pointing at the relevant Ayzeo settings page. Your AI assistant can read this and tell you exactly how to connect the missing integration, rather than failing silently.

Yes. Tokens are per-project so a compromised token exposes only that one project. All traffic runs over HTTPS. The server is stateless (no session caching of token data), Pro-plan gating is enforced per request, and the shared apiLimiter prevents runaway usage. No credentials from the AI client ever reach Ayzeo beyond the bearer token.