MCP App Store
by KeenEthics
CitationLab Marketing Manager icon

CitationLab Marketing Manager MCP Server for ChatGPT

By CitationLab

Overview

CitationLab Marketing Manager connects ChatGPT to your marketing workspace, so you can ask about your own projects and follow up on them without leaving the conversation. What you can do: - AI search visibility: see how your brand shows up in AI assistants and AI search answers — mentions, citations, share of voice and the competitors that are cited instead of you. - SEO: Search Console queries and pages, tracked keyword rankings, cannibalization, technical SEO audits and index status. - Analytics: GA4 traffic, sources, page engagement and conversions. - Paid media: Google Ads, Meta, LinkedIn and Microsoft Ads performance. - Competitors and links: head-to-head comparisons, competitor activity and your backlink overview. - Actions: see open actions and recommendations, and turn findings into tracked actions with owners, priorities and status. You sign in with your CitationLab account and approve the connection. ChatGPT only sees the projects your account can already access. Everything except creating, updating and commenting on actions is read-only, and every change goes through the same permissions as the app itself. Requires a CitationLab Marketing Manager account on a plan that includes AI connectors.

How to connect

  1. ChatGPT: Open the CitationLab Marketing Manager listing in the ChatGPT app directory and choose Connect. ChatGPT listing CitationLab Marketing Manager exposes 88 tools here.

Tools

add_action_comment

ChatGPT
Adds a comment to an existing action in a project's CitationLab workspace without changing the action's status. It can notify stakeholders and mentioned users and may send stakeholder emails according to notification preferences; delivered emails cannot be recalled. Each successful call creates a new comment; retrying can post duplicate comments and notifications.

create_action

ChatGPT
Creates a new action (a tracked task) in a project's CitationLab workspace, with title, description, priority, status, due date, assignee and links to KPIs and goals. Returns the action with its key (for example ELNO-142).

create_gbp_post

ChatGPT
Creates or schedules an Update, Event or Offer. Select a project Media Library image or public mediaUrl. scheduledAt is a future RFC3339 publish time. Event/Offer require title and local start/end dates, with optional times. recurrence supports DAILY, WEEKLY (daysOfWeek) or MONTHLY (dayOfMonth or dayOfWeekOccurrence), optionally ending at seriesEndAt. Google decides the publication state; processing, scheduled or rejected does not mean live. Use get_gbp_post/update_gbp_post to edit an existing post.

create_gbp_service

ChatGPT
Add one service to the live Google profile while preserving all other services. Supply expectedVersion from list_gbp_services and either a predefined serviceTypeId or a custom label/category. Google supports a fixed price or no price. The returned changed flag tells whether a write happened.

delete_gbp_media

ChatGPT
Deletes a photo or video from a Business Profile location. Ids come from list_gbp_media.

delete_gbp_post

ChatGPT
Deletes a post from a Business Profile location (and from Google Search and Maps). Post ids come from list_gbp_posts.

delete_gbp_review_reply

ChatGPT
Removes the business owner's reply from a Google review. changed: false means the review had no reply.

delete_gbp_service

ChatGPT
Remove one service from the live Google profile, preserving other services. Requires its key and expectedVersion from list_gbp_services.

get_action

ChatGPT
Gets a single action/tiltak by id or key, with the full field set — everything list_actions returns plus description and the taxonomy/prioritization fields create_action and update_action can write (categoryId, workTypeId, tags, abcPhase, RICE fields, valueTypes, kpiIds, goalIds, planPointId, assigneeId, linkedUrlId). Use this when you need one action's complete record instead of paging through list_actions. kpis gives each linked KPI's id AND name together — refer to a KPI by its name in any prose/comment you write, never by the bare numeric kpiId.

get_ai_citations

ChatGPT
AI Monitor citations aggregated by source. view=domains (default) returns cited domains with mention_count, url_count, avg_position, avg_sentiment, share_pct, last_seen, conversions; view=urls returns the cited URLs (AI landing pages). Pass detail=<domain|url> for a drill-down (per-topic/prompt/model/day breakdown).

get_ai_competitors

ChatGPT
AI Monitor competitor visibility: brands extracted from AI responses merged with the manual competitor registry. Returns { name, categories[], frequency, urls[] } per competitor.

get_ai_mentions

ChatGPT
AI Monitor brand mentions extracted from LLM responses. view=brands (default) returns { name, category, categories[], totalMentions, promptCount, promptTitles[], modelCount, models[], urlCount, urls[], domains[], lastSeen }; view=urls returns mention URLs with { url, domain, totalMentions, brandNames[], brandCount, models[], prompts[] }.

get_ai_model_performance

ChatGPT
AI Monitor per-model performance. view=overview (default) returns provider cards (visibility/citation/mention/sentiment per LLM & SERP); view=comparison returns the detailed comparison table.

get_ai_monitor_report

ChatGPT
Get complete AI Monitor visibility report: topics + recent queries + brand sentiment + overview

get_ai_prompt_responses

ChatGPT
Get AI query responses for a specific prompt

get_ai_share_of_voice

ChatGPT
AI Monitor share of voice (CAVIS): per-brand citation share, mention share, visibility score and sentiment over the window. Reads cached scores; does NOT recompute. A provider filter (model / models / serps) narrows every part of the result — KPIs, leaderboard, model comparison, prompt breakdown and dataQuality — to those providers' answers; topic/prompt/funnel/tag/scope filters compute live.

get_ai_visibility_change

ChatGPT
Is AI visibility really rising or falling? Compares the window (default the last 30 days) with the previous window of the same length for the Visibility Index, citation rate (runs that cited the project's own domains), mention rate (runs that named its brand) and visibility rate (cited or named) — the dashboard's Visibility change card. Each metric returns { current, previous (0-100, over every run), rawChange (points, all runs), change (points, like-for-like: only prompts that ran in both windows, each weighted by its runs), ci {lower, upper} (95 %), significant, direction ('rising' | 'falling' | 'flat'), reason ('significant' | 'within_noise' | 'no_data' | 'no_previous_data' | 'too_little_data') }. A direction is only given when the change is statistically significant. A gap between rawChange and change means the prompt set changed, not the answers. Also returns period, matchedPrompts, totalPrompts, reliability ('none' | 'low' when too few prompts ran in both windows | 'good') and excludedDays { current, previous }: the days left out of every number because not all of the project's prompts ran on them, each { date, promptsExpected, promptsRun }. Read-only.

get_ai_visibility_trend

ChatGPT
AI Monitor daily visibility trend for a project, same own-brand definition as the dashboard KPI cards: per-date { date, visibility (Visibility Index 0-100), citationProbability (own-domain citation rate %), mentionProbability (own-brand mention rate %), citationShare %, mentionShare %, ownCitations, ownMentions, citations (all), mentions (all), mentionProbabilitySmoothed/Lower/Upper (trailing-window 95% Wilson band), windowSampleSize, queriesCount }.

get_analytics_overview

ChatGPT
Gets Cite Analytics overview with daily stats for a project

get_bing_ads_metrics

ChatGPT
Get Bing Ads performance metrics for a project.

get_business_profile

ChatGPT
Gets a project's business profile data, including brand voice and visual identity

get_competitor_head_to_head

ChatGPT
Gets the "us vs. them" Head-to-Head comparison for one competitor — AI citations/mentions, organic + paid traffic and keywords, topic coverage, and keyword overlap, each with a winner. The same computation the Head-to-Head page and its PDF export use, so an agent can read the comparison without the browser. Pass a competitor id from list_competitors.

get_competitor_weekly_digest

ChatGPT
One ranked overview per competitor for a period, merged from Web Spy, Sitemap Watch and Feed Watch — the call to make for a weekly competitor report instead of reading each module per agent. Each entry holds only what matters: Web Spy changes rated medium or above after grounding (minor ones are counted, not listed), new and removed sitemap URLs grouped by theme (the first path segment, e.g. forbrukslan, refinansiering), lastmod-only churn as a count, and new feed posts with their AI signal. health flags a competitor that appears to have shut down (Sitemap Watch lost the sitemap AND the site looks gone: a critical Web Spy change, every agent failing, or the feed failing) or whose monitoring keeps failing (e.g. an agent switched off after repeated errors), and lists the watches worth pausing. openShutdownAlerts lists competitors whose "appears to have shut down" alert is still open (it closes by itself, with a "back online" alert, once the sitemap — or, for a site whose pages had failed, the pages — can be read again). Ranked by score (critical change 10, high 6, medium 2; 2 per new URL theme, 1 per removed; launch/pricing post 4; a likely shutdown +100). Things watched without a competitor link are attributed by domain; anything still unmatched is its own entry named by host. Read-only; spends nothing.

get_ga4_events

ChatGPT
Gets GA4 conversion/event data showing event counts, users, and event values, totalled per event name. It has no dimension filter: to split ONE event by source, medium, page or an event parameter (e.g. form_location), use analytics.event_breakdown (source=ga4; dimension session_source, session_medium, page_path, device_category, country or properties). The source/medium/page/device/country splits are cached only for events that are an active GA4 conversion definition or a funnel step, so for any other event they come back empty (not zero data: make the event a conversion first); properties and event_property_values read GA4 live and analytics.event_property_values (the values of one registered custom dimension, with an optional date range).

get_ga4_page_engagement

ChatGPT
Gets GA4 page-level engagement data showing pageviews, engagement rate, time on page, bounce rate, entrances per page

get_ga4_summary

ChatGPT
Gets a comprehensive GA4 analytics summary for a project including totals, top sources, top pages, device breakdown, and top countries

get_ga4_traffic_sources

ChatGPT
Gets GA4 traffic sources breakdown by source/medium/channel with sessions, users, bounce rate, and conversions

get_gads_metrics

ChatGPT
Gets Google Ads metrics by entity type (campaign, ad_group, ad, keyword, search_term, or auction_insight). There is no account/customer-level entity type — for account totals, aggregate the campaign rows.

get_gbp_insights

ChatGPT
Read legacy cached monthly summaries with unverified coverage. Retired search/photo metrics and uncertain zero defaults are null. Prefer get_gbp_performance for current metrics, measured zeros, date ranges and coverage.

get_gbp_location_profile

ChatGPT
Read the live profile before editing: name, description, primary/additional phones and categories, address, regular/special/additional hours, opening date, service area, status, services and editing eligibility. Returns profileVersion and servicesVersion to detect stale changes. Use separate service CRUD for individual services, and booking/profile-links operations for booking, social and messaging links.

get_gbp_performance

ChatGPT
Performance for one location over an inclusive date range: Search/Maps views by device, call/website/direction/message/booking/menu clicks, daily series, monthly search terms, and synced-review counts. Optional previous-period comparison. Missing data remains unavailable; search-term thresholds are not exact counts. Google does not expose all native audience or product reports through this connection.

get_gbp_post

ChatGPT
Read a current Google post and its edit version, recurrence, publication state and scheduling eligibility. Read this before update_gbp_post. An unsupported post stays available in Google's editor.

get_gbp_product_management

ChatGPT
Find the location's product-management handoff. Google Business Profile does not expose Product Editor create/update/delete through its public API. Use the returned Google profile link and Edit products; linked accounts may open Merchant Center. This operation does not claim to publish or modify products.

get_gbp_profile_attributes

ChatGPT
Read the BOOL, ENUM and REPEATED_ENUM business details Google makes available for this location, grouped by category with exact choices, current values and a version. These include eligible accessibility, amenities, service and payment details. Unspecified is different from No. URLs and social links use get_gbp_profile_links.

get_gbp_profile_health

ChatGPT
Manager's profile-completeness assessment for each project location, including missing details, unknown checks and data freshness. This is not Google's private strength or ranking score.

get_gbp_recommendations

ChatGPT
Location-specific next steps using the profile, reviews, posts, active strategy, planned campaigns and saved seasonal search history. Returns evidence and whether an Update, Offer or Event may fit. Suggestions never publish anything or invent an event, price or discount.

get_gbp_reviews

ChatGPT
Read a page of synced Google reviews, including owner-reply moderation status, policy reason and Google reply URL. Pending, rejected or unknown replies are not approved. Continue with nextOffset while hasMore is true.

get_gsc_cannibalization

ChatGPT
Keyword cannibalization from Google Search Console: queries for which two or more of the project's own URLs take impressions in the period, with each URL's clicks, impressions, average position and share of the query's impressions, the page that should own the query, the recommended method (merge, canonical, redirect, differentiate, or double_listing — two top-3 results, usually a gain) and the clicks the conflict costs. sectionPages lists competing pages other pages of the site sit under (the home page, a blog index): those are never merged or redirected — the method is differentiate, and the content page owns the query. Worst first. Pass 'keywords' to check specific queries; without it the property's top query×page rows are scanned. Spellings of one page (http/https, www, trailing slash, query string) count as one page. Brand searches and queries tagged brand or ignore on Analytics → GSC → Cannibalization are left out. Same rule as that tab (shared/cannibalization.ts, explore floor: a page counts from 2 impressions, and the competing pages need 5+ between them). Read live from the Search Console API. competingSince is the first day of the unbroken run of daily checks that saw the conflict (the stricter inbox floor on the stored 28-day window, recorded after each Search Console sync); null when the daily check has not seen it.

get_gsc_full_report

ChatGPT
Get complete Google Search Console report: period totals + top keywords + top pages, all properly aggregated.

get_gsc_keywords

ChatGPT
Gets Google Search Console keyword/query data aggregated across all days in the period. Returns accurate totals plus top keywords by impressions. Check dataCompleteness.isComplete before trusting the totals as covering the whole requested period — missingDates lists any day inside the reporting window (GSC's normal ~3-day lag) that never synced, and lastSyncedAt says when this site's data was last touched by a sync. Pass 'keywords' to filter to specific exact queries and get a per-page breakdown (which URL ranks for each). Pass 'granularity' to get a day/week/month time series in one call instead of one flat total for the whole period.

get_gsc_pages

ChatGPT
Gets Google Search Console page performance data. When startDate/endDate are given explicitly, the response is scoped to exactly that period (fetched live from Google — see source). With no explicit period, it serves the latest synced snapshot for speed, which is a rolling ~400-day cumulative window rather than a fixed period — check note/asOf to tell the two cases apart.

get_index_checker_report

ChatGPT
Get complete index checker report for a project: all tracked URLs with their latest check results

get_integration_status

ChatGPT
Reads the connection status of every marketing/analytics integration (Google Ads, GA4, Google Search Console, Meta Ads, GTM, WordPress, Contentful, Prepr, Sanity, Webflow, HubSpot, Umbraco) for a project in ONE call. Use this before calling an integration-specific tool (gtm., google_ads., ga4., search_console., cms.*) to check whether it is connected, instead of discovering 'not configured' one tool at a time. google_ads/ga4/gtm each carry hasOAuthToken separately from connected: connected means an id has been selected (customer/property/container), hasOAuthToken means this project has authorized that Google service at all. If hasOAuthToken is true but connected is false, connect_google_ads / connect_ga4 / connect_gtm can select an id without a new OAuth handshake; if hasOAuthToken is false, OAuth must be granted first via the Integrations page. Read-only.

get_kpi_trend

ChatGPT
Gets KPI trend data (daily values) over a period

get_linkedin_ads_metrics

ChatGPT
Gets LinkedIn Ads performance metrics for a project

get_meta_ads_daily_metrics

ChatGPT
Get Meta (Facebook/Instagram) Ads daily performance rows for a project — the right source for week-over-week or day-level comparisons. Populated by meta_ads_sync / the 12h scheduler; empty until at least one sync has run.

get_meta_ads_metrics

ChatGPT
Get Meta Ads monthly performance metrics for a project. For day/week-level numbers (e.g. week-over-week comparisons) use get_meta_ads_daily_metrics instead — this tool only returns one row per entity per calendar month.

get_openai_ads_metrics

ChatGPT
OpenAI Ads (ChatGPT ads) performance for a period: impressions, clicks, cost, conversions, CTR (%), average CPC, cost per conversion and conversion rate (%) per campaign, ad group or ad, with the campaign / ad group each belongs to, the period totals and currency (the ad account's). granularity: "day" adds a per-day series per entity and per-day totals, for trends and monthly reports. Totals add up one level only — never add campaign and ad group rows together. Reads the data the account sync stores (refreshed by the scheduled sync and by sync_openai_ads_account); coverage says how many days in the period have data and lastSyncedAt when the newest data arrived. Read-only.

get_project

ChatGPT
Gets details for a specific project by token, name, or domain

get_project_summary

ChatGPT
Gets a comprehensive summary of a project including counts of keywords, actions, and analyses

get_rank_tracking

ChatGPT
Gets rank tracking keywords and their positions for a project, one device at a time (desktop by default; mobile only exists for keywords the project opted into mobile tracking for). Each keyword carries the SERP features present in its latest check (and whether the project owns each) and the positions of the project's competitors in that same SERP.

get_ranking_history

ChatGPT
Gets ranking position history for one tracked keyword over time. Identify the keyword EITHER by keywordId (from list_keywords) OR by projectId + keyword (the keyword text, matched case-insensitively among the project's tracked keywords) — the second form is what a diagnosis that names a search term can call directly.

get_recommendation

ChatGPT
Get a single recommendation with full context: business case (linked KPIs, keyword reach, URL scope, finding counts), linked actions, supporting findings (with source data), and event history. Use this when you need to understand the rationale, root cause, hypothesis, expected outcome, and quantitative anchors behind a rec before acting on it.

get_referrers

ChatGPT
Gets traffic referrer/source data for a project's website. Every row carries its channel (Organic Search, Paid Search, AI Assistant for ChatGPT / Perplexity / Gemini / Copilot / Claude, Referral, Direct, …) and channelTotals sums sessions per channel over the whole period, so AI traffic shows as its own channel.

get_technical_seo_full_report

ChatGPT
Get complete technical SEO audit report: audit details + all pages + all issues + all links in one call

get_technical_seo_issues

ChatGPT
Get issues found in a technical SEO audit. Optional filters (title, category, type, impact, pageId) are applied before the limit.

get_top_pages

ChatGPT
Gets the most visited pages for a project's website

list_action_comments

ChatGPT
Lists comments on an action/tiltak

list_actions

ChatGPT
Lists project actions with typed primary assignees. Filter assignee: cita for delegated work. agentReady is a deprecated read-only alias derived from Cita primary assignment. Done stays assigned; blocked runs wait with a report comment. kpis gives each linked KPI's id AND name together — refer to a KPI by its name in any prose/comment you write, never by the bare numeric kpiId.

list_ai_prompts

ChatGPT
List AI Monitor prompts for a project. Per prompt, over ALL its completed runs (AI models and search engines alike): citationCount = citations of the project's own domains, mentionCount = mentions of the project's own brand, citationRate / mentionRate = share of completed runs (0-1) that cited / named the brand (null before the first completed run). For a date window use the visibility tools.

list_competitors

ChatGPT
Lists all competitors for a project

list_gads_campaigns

ChatGPT
Lists Google Ads campaigns for a project, one row per campaign per month (newest month first). Without filters it returns every campaign (including REMOVED) for every synced month, which can be very large — narrow it with status, yearMonth or startMonth/endMonth.

list_gbp_locations

ChatGPT
Lists Google Business Profile locations for a project

list_gbp_media

ChatGPT
Lists the photos and videos on a Business Profile location, newest first, with the id delete_gbp_media takes. Media view counts are unavailable through the current Google API; null is not zero.

list_gbp_posts

ChatGPT
Lists updates, events and offers on a Business Profile location, including scheduled, processing and rejected posts, newest first, with the id delete_gbp_post takes. scheduledAt is an absolute planned publication time; publishedAt is set only for live posts. eventStartDate and eventEndDate encode the location's local calendar date and time in UTC fields; do not convert those event fields to another timezone.

list_gbp_services

ChatGPT
Read a location's current predefined and custom services, prices, editing eligibility and version. Read before a service create/update/delete so an outdated form cannot replace a newer service list.

list_keywords

ChatGPT
Lists keywords for a project with search volume and ranking data. Supports substring or exact search, exact batch lookup by keyword text, and intent/hasVolume filters — use this instead of paging through the whole pool to check a handful of keywords. Volume comes as searchVolume (Google search volume from the Keyword Planner when fetched, otherwise the AI-assistant volume — searchVolumeSource says which: 'google' | 'ai' | null) plus the two raw figures googleSearchVolume and aiSearchVolume, which measure different demand and are not interchangeable.

list_kpis

ChatGPT
Lists KPIs for a project. measurementTrust is set when the Lab Brain diagnosis has the measurement behind a KPI in doubt (suspect/broken) — check that before acting on a move in it.

list_meta_ads_campaigns

ChatGPT
List Meta (Facebook/Instagram) Ads campaigns for a project — returns id, name, status, objective and budgets, as last synced from the connected Meta ad account.

list_projects

ChatGPT
Lists all projects in CitationLab with their details. Archived projects are left out unless includeArchived is true — every other tool refuses an archived project until it is restored in the app.

list_recommendations

ChatGPT
List recommendations for a project with full business case enrichment. Each row includes linked KPIs (current/forecast/target/gap), keyword search-volume reach, URL scope (count + examples), source-finding counts, and persona count — whichever quantitative anchors are available on the rec. The response carries total (the full count of the filtered set) and limit/offset alongside recommendations, so a filtered set larger than one page is never mistaken for the complete set — page through with offset when total exceeds offset + recommendations.length.

list_technical_seo_audits

ChatGPT
List technical SEO audits for a project

reply_to_gbp_review

ChatGPT
Submits the business owner's reply to a Google review, replacing an existing reply unless ifUnanswered is set. Google may approve, moderate or reject it; inspect the returned status rather than assuming it is public. Review ids and moderation details come from get_gbp_reviews. Max 4096 bytes.

search_gbp_categories

ChatGPT
Searches Google's Business Profile category list by name (e.g. "car repair", "bilverksted"). Returns each category's id (categories/gcid:…) for update_gbp_location's primaryCategory / additionalCategories, and the category's predefined services (serviceTypeId) for its services.

update_action

ChatGPT
Updates an existing action in a project's CitationLab workspace. Supplied fields replace existing values; omitted fields stay unchanged. KPI, goal and assignee arrays replace their current relationship sets, and empty arrays remove all links in that set. Status changes can close or cancel the action and update a mirrored experiment. An optional comment is posted after the update and may send stakeholder email notifications; retrying with a comment can post it again.

update_gbp_location

ChatGPT
Update the public Google profile with only the fields being changed: name, website, phones, description, categories, address, regular/special/additional hours, opening date, service area and business status. Read get_gbp_location_profile first and pass its profileVersion as expectedVersion; a stale form is refused. Category and service IDs come from Google's category lookup. Omitted fields remain unchanged. Legacy services replaces the complete list; prefer create/update/delete_gbp_service for one service. changed:false means no Google write happened.

update_gbp_post

ChatGPT
Edit an existing Update, Event or Offer. Requires expectedVersion from get_gbp_post and only the changed fields in changes. Empty strings clear optional fields; recurrence:null stops recurrence. Unchanged images and recurrence are preserved. Choosing an image replaces the entire media selection. Only still-scheduled posts can be rescheduled. Google decides the resulting publication state.

update_gbp_profile_attributes

ChatGPT
Set or clear eligible business details. Read get_gbp_profile_attributes first and supply its expectedVersion; send only changed attributes with exact names/types/choices. BOOL/ENUM use values, REPEATED_ENUM uses setValues (Yes) and unsetValues (No), with choices absent from both unspecified. clear:true resets an entire detail to unspecified. Never invent business claims or replace unknown existing values.

update_gbp_service

ChatGPT
Edit one live service using its key and the latest services version. Preserve omitted prices; price:null removes a price. This changes the public profile and preserves unrelated services.

upload_gbp_media

ChatGPT
Add a photo or video to a Business Profile. Select a project Media Library image with mediaAssetToken, or provide a public sourceUrl. Selected library images are prepared in a compatible format. category controls placement; PRODUCT is a photo category and does not create a product-catalog entry.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/citationlab-marketing-manager"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/citationlab-marketing-manager)