MCP server: connect your AI assistant
Encited ships a remote MCP (Model Context Protocol) server, so any MCP-capable AI assistant can work with your Encited data directly: pull crawl analytics, inspect cached snapshots, read AI-mention results, and — with your permission — start SEO audits and content workflows.
The MCP server is available on every plan, including trials. Your connection permissions determine whether write tools appear. Your plan determines which tools you can use — see the table below.
Connect your assistant#
The server lives at:
https://encited.com/api/mcp
Authentication is OAuth — your assistant opens a browser window where you sign in to Encited and approve the connection. No API keys to copy.
ChatGPT: Settings → Apps & Connectors → Advanced settings → enable Developer mode (required for custom connectors), then Create connector: give it a name, paste the URL above, choose OAuth authentication, and complete the sign-in when the browser opens.
Claude (claude.ai): Settings → Connectors → Add custom connector, paste the URL above, and complete the sign-in when the browser opens.
Claude Code:
claude mcp add --transport http encited https://encited.com/api/mcp
Then run /mcp in a session to trigger the sign-in.
Codex (CLI): add the server to ~/.codex/config.toml:
[mcp_servers.encited]
url = "https://encited.com/api/mcp"
Then run codex mcp login encited to trigger the sign-in.
Cursor: add the server to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"encited": {
"url": "https://encited.com/api/mcp"
}
}
}
Then complete the sign-in when Cursor prompts you.
The consent screen#
When you approve a connection you choose two things:
- Which accounts the assistant acts on: your personal account, the teams you belong to, or several of them. Tick every account the connection should reach. To change the list later, connect again.
- What it may do:
| Permission | What it allows |
|---|---|
| Read | Read domains, snapshots, crawl analytics, Search Console data, SEO audit results, Index Rush data, workflow results, AI mentions |
| Write | Start SEO audits, content workflow runs, and re-renders, which consume your plan's audit quota, workflow credits, and renders. Remove snapshots, which consumes nothing |
Write access is offered when your role allows it (editor or above) in at least one account you tick. If you are a viewer in all of them, the connection is read-only. In an account where you are a viewer, write tools are refused.
What your assistant can use, by plan#
Everything below inherits your existing plan limits — audit page quotas, workflow credits, daily caps — exactly as in the dashboard.
| Tools | Basic | Essential | Business and above |
|---|---|---|---|
| Domains, snapshot cache, crawl analytics, Search Console | ✓ | ✓ | ✓ |
| SEO audits (read + start) | ✓ | ✓ | ✓ |
| AI Mentions (prompts, runs, competitors, citations) | ✓ | ✓ | ✓ |
| Index Rush | ✓ | ✓ | |
| Content Workflows (read + start) | ✓ | ✓ | |
| AI fan-out queries | ✓ |
Read tools remain listed across plans. Write tools appear only when the connection has write permission. Calling a tool outside the account's plan returns the required plan and an upgrade link. An inactive subscription blocks account-data tools, while onboarding guidance remains available. Every call also checks the user's current account and domain access.
Tool reference#
Tools marked write require write permission on the connection.
General
read_me— read tool guidance and practical playbooks for article research, rank checks, competitor analysis, citation opportunities, AI fan-out queries, content plans, audits, and client reports.get_middleware_setup— read the site's middleware snippet, platform installation steps, secret location, and links to setup, authentication, and verification guides. This tool does not deploy code or change hosting.verify_middleware(write) — check that crawler requests reach Encited with valid authentication. A successful check can activate a pending site's API integration.list_teams— the teams the connection covers, each with its id, your role, and its domains. It appears only when the connection covers several accounts. Every other tool then takes a team id in itsteamargument.list_domains— the domains in one account; the starting point for its other tools.add_domain(write) — add a site to the account. An account with no sites can always add its first one. More sites need the Essential plan or above.
Snapshot cache
list_snapshots— cached prerendered pages for a domain, with age and size.get_snapshot— one cached page's metadata and SEO analysis, optionally with the rendered HTML.rerender_pages(write) — re-render up to 50 pages now, for example after a fix is deployed. Each page uses one render.rerender_site(write) — start a site-wide re-render in the background: every page, only sitemap pages updated since their snapshot, or only snapshots older than a number of days. Each page uses one render.get_render_job— progress of arerender_sitejob. Pages the site no longer serves (404, 410, or a page that says it is not found) are counted as not found, not as failures.remove_snapshots(write) — remove the snapshots of up to 50 paths, for example pages deleted from the site. Crawlers then get your site's own response for those paths. Uses no renders.remove_stale_snapshots(write) — remove snapshots in bulk: every page your sitemap no longer lists, or every snapshot of the site. A large site returns a cursor to continue with. Uses no renders.
Re-render and remove tools need the editor role on the domain.
Crawl analytics
query_crawl_logs— recent bot and crawler visits, filterable by provider, path, status, outcome, category, and bot check (IP check passed or failed, or ignored robots.txt).get_crawl_stats— aggregate crawl activity: top crawlers, pages crawled, crawl-budget savings, per-day breakdown.
Google Search Console
get_gsc_connection_status— whether Search Console is linked for a domain and whether ownership is verified.connect_gsc_property(write) — a link you open to connect Google Search Console for a domain. Sign in with the Google account that owns the site, then go back to your assistant. The link works for 1 hour.get_gsc_keywords— top search queries with clicks, impressions, click-through rate, and average position.get_gsc_page_analytics— impressions and clicks per page, best performers first.get_gsc_site_health— totals for the period: clicks, impressions, average position, pages with impressions.inspect_gsc_url— one URL's index status straight from Google, including why it isn't indexed.
SEO audits
list_seo_audit_runs— audit history with health scores and issue counts.get_seo_audit_run— one audit's per-page results (issues, head fields, content metrics), worst pages first.get_seo_audit_page— one audited page's full record: head fields, social tags, response metadata, and internal links.get_seo_audit_issues— current issues across the domain, grouped by type.start_seo_audit(write) — start a crawl: follow links, audit selected URLs, or discover from the sitemap.
Index Rush — Essential and above
get_index_rush_pages— sitemap pages joined with Google index status and inbound-link coverage.get_index_rush_inbound_links— which indexed pages link to a not-yet-indexed target.
Content Workflows — Essential and above
list_workflows/get_workflow— read workflow descriptions, result types, estimated credit costs, and the name of each execution tool. Inputs are declared on each execution tool.get_workflow_credits— read your credit balance for the current cycle.write_article(write) — research search results and save an article draft with an outline, FAQs, structured data, and link suggestions.refresh_page(write) — research an existing page and competing results, then save a revised draft and change list.build_content_plan(write) — save a content plan from keywords, competitor gaps, or stored AI visibility gaps.build_refresh_plan(write) — prioritize existing pages to improve using ranking opportunities and available Search Console history.check_serp_position(write) — check the first 20 Google results for one query, location, and device.analyze_serp(write) — research ranking pages, search intent, topics, and content patterns.audit_search_console(write) — analyze connected Search Console data and save a prioritized fix plan.write_service_area_pages(write) — research a business and save up to ten service-area page drafts.audit_local_seo(write) — research the business profile, reviews, local competitors, and service-area coverage.research_competitor(write) — compare a competitor's ranking keywords, page groups, domain metrics, and backlink gaps with your site.find_link_gaps(write) — find relevant sites linking to competitors but not to your site.scan_map_grid(write) — scan a Google Maps grid for one keyword by default, or all supplied keywords when requested.list_workflow_runs/get_workflow_run/get_workflow_result— read run history, progress, and saved output.share_workflow_result(write) — enable public link access to a successful result and its visible run inputs. Anyone with the link can read them. Revoke access on the run page; copies already downloaded cannot be removed.
Workflow execution consumes credits and requires editor access and an active eligible subscription. The tools save drafts or recommendations in Encited. They do not publish website pages or send outreach. Refresh your assistant's tool list after this update. The generic start_workflow and the old get_workflow_result_share_link name have been removed.
AI Mentions
list_ai_prompts— the prompts monitored for a domain.list_ai_prompt_runs/get_ai_prompt_run— per-provider run results: mention position, sentiment, citations, analysis.list_competitors— brand vs competitor visibility across AI answers.list_citations— the domains AI providers cite, with counts and classification.list_fanout_queries— the web searches providers ran while answering (Business and above).
Managing connections#
Every connected assistant appears in Settings → Connections, with its name, the accounts it reaches, its permissions, and its connection date. Revoking a connection cuts the assistant off immediately — its next request fails and it must re-authenticate.
On Business and Enterprise plans, connection approvals and revocations are recorded in the audit log under the MCP category.
Good to know#
- New to Encited? If you sign up while connecting, the approve screen gives you a few prompts to start with. Paste the first one into your assistant and it walks you through setup: add your site, connect Search Console, track your brand in AI answers, run an SEO audit, and research a competitor.
- Changed your plan? Access is checked on each call. If the tool list itself changes after a server update, refresh or reconnect the connector so your assistant sees the current tools.
- Your assistant knows its way around. The server ships built-in usage guidance: when it connects, your assistant learns which tool fits which task (from "is Google crawling my site?" to "check Search Console for growth opportunities") without you having to explain the toolkit.
- Write tools missing? Your connection is read-only: either you did not grant write access, or your role allows it in none of the accounts you ticked. Connect again and approve write access with an account where you are an editor or above.
- Left a team, or the plan lapsed? Membership and billing are checked on each request, for the account of that request. A team you left drops out of the connection, and the others keep working. An inactive subscription blocks that account's data, while setup guidance remains available.
- Rate limits. Each account gets 120 MCP requests per minute — far more than an assistant needs in normal use. Over the limit, requests return a
rate_limitederror with aRetry-Afterheader; the assistant can simply wait and retry. - Assistants never see raw API keys or the data of accounts outside the connection; every request is re-checked against your current membership, role, and plan.
