Cleotic
Server Details
AI brand visibility, competitor mentions and citation evidence for agents. Cleotic account required.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 50 tools
Most tools target distinct resources or actions, and the descriptions explicitly separate close pairs like act_on_opportunity vs update_opportunities and get_reputation vs get_perception. However, the analytics surface still has several related get/list tools whose boundaries require reading long descriptions, and multi-view getters add selection burden.
The tool set is overwhelmingly snake_case with predictable verb_noun patterns such as list_*, get_*, create_*, and search_*. Minor deviations include save_* being used for create/edit/pause/resume operations, generic delete_item, and the split between set_primary_brand and update_brand.
The platform is broad, but 50 tools is far beyond a well-scoped agent-facing surface and forces substantial tool-selection overhead. Many niche operations are individually justified in the product, yet the set is too heavy for the apparent MCP purpose.
Coverage is broad across brand setup, monitoring, opportunities, Content Studio, readiness, citations, reports, facts, and documentation. Some lifecycle gaps remain, such as no get_report for inspecting an existing report and no clear brand or fact deletion path, but the core workflows appear workable.
Publisher details
- Operator
- Cleotic
- Operator website
- https://cleotic.ai
- Vendor relationship
- Not applicable
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Paid plan required.
Available Tools
50 toolsact_on_opportunityAct on opportunityAInspect
Record or start an opportunity's play, which moves it to watching. Use it rather than update_opportunities whenever the play was done, so the inbox knows what to watch for. fix_shipped: a readiness fix is live. pitched: a source gap's outreach was sent. optimised: a traffic gap's page was improved. track_prompts: track the chosen suggested questions as prompts. draft_outreach: draft a source gap's outreach; Cleotic never sends it. Cost: track_prompts uses one active prompt of plan capacity per question and model budget for their first answers; draft_outreach uses one from the Content Studio allowance and model budget; the others are free.
Inputs: brand (required), action (required), opportunity_id (required), idempotency_key (required), +1 more. Returns: data, generated_at, schema_version
approve_brand_setupApprove brand setupAInspect
Create the brand from a ready setup's proposals. List exactly the competitor and prompt proposals to keep; an empty list keeps none of that kind, and the primary brand is always kept. Confirm the brand's market with the user first and pass it as market; get_brand_setup's segment.market and market_label give its code and label. Cost: a brand, a segment and the kept prompts from plan capacity; model budget for each prompt's first answers and the site's first readiness scan.
Inputs: setup_id (required), idempotency_key (required), accepted_brand_proposal_ids (required), accepted_prompt_proposal_ids (re… Returns: data, generated_at, schema_version
comment_on_opportunityComment on opportunityCInspect
Add a comment to an opportunity as you.
Inputs: body (required), brand (required), opportunity_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
create_pageCreate pageAInspect
Start a Content Studio page and hand it to Cleotic's page agent: from a content gap opportunity, a question or idea, an existing draft in Markdown, or a URL to import. The agent first sets the page's goal, reader and angle, then proposes an outline, asking only for facts it is missing. Returns pending while it works; read its questions with get_page and answer them with message_page. Cost: one of the plan's Content Studio pages, counted once the agent first writes the page; model budget.
Inputs: brand (required), idempotency_key (required), url, idea, +3 more. Returns: data, generated_at, schema_version
create_reportCreate reportAInspect
Save a shareable report of the brand's results for a date range, compared with the same number of days before. Returns its public link at once; the link shows the report once its figures are built, usually within a minute. Cost: one report of plan capacity; on plans with report narratives, model budget for its summary.
Inputs: brand (required), idempotency_key (required), to, from, +1 more. Returns: data, generated_at, schema_version
delete_itemDelete itemADestructiveInspect
Delete one competitor, segment, prompt, page, or report for good: pass exactly one of its IDs. It cannot be restored. Deleting a segment deletes its prompts and their answers; deleting a prompt deletes its answers. To stop tracking but keep the history, pause it with save_competitor, save_segment or save_prompt; to only kill a report's link, use revoke_report. Free, and frees the plan capacity the item used.
Inputs: brand (required), idempotency_key (required), page_id, segment, +3 more. Returns: data, generated_at, schema_version
edit_pageEdit pageAInspect
Change a page yourself: replace its Markdown, or make exact find-and-replace edits, and edit its title, goal, reader or angle. Pass base_version from get_page; a stale version is refused so you don't overwrite a teammate. A live page is locked: revise_page first. Free.
Inputs: brand (required), page_id (required), idempotency_key (required), goal, +7 more. Returns: data, generated_at, schema_version
get_ai_trafficGet AI trafficARead-onlyIdempotentInspect
AI crawler requests and AI-referred visits to the brand's site, from its tracking; connected is false when tracking is not set up. Visits are human page views; bots, crawlers and Cleotic's own fetches are never visits. AI share is AI-referred visits as a percentage of human visits; crawler requests are counted on their own. view summary: totals, providers, crawlers, search engines (listed, never counted), referral sources, pages to improve, by week. view pages: per-page traffic. view evidence: individual visits. Only pages and evidence are paged.
Inputs: brand (required), to, from, path, +6 more. Returns: data, generated_at, schema_version
get_answerGet answerARead-onlyIdempotentInspect
One AI answer in full, with the brands it mentions, its recommendations, ranked list, outcome, and citations. Use it to read an answer_id from list_answers; to scan many answers use list_answers.
Inputs: answer_id (required). Returns: data, generated_at, schema_version
get_brand_overviewGet brand overviewARead-onlyIdempotentInspect
The brand's Overview in one call: visibility, share of voice and recommendation with their basis and change, how the brand and its main competitors stand, and headline readiness, traffic, inbox and Content Studio status. For one slice in depth use get_perception, list_citations, get_ai_traffic or get_readiness. A segment filters the answer metrics.
Inputs: brand (required), to, from, segment. Returns: data, generated_at, schema_version
get_brand_settingsGet brand settingsARead-onlyIdempotentInspect
Read the brand's settings: primary brand, competitors, segments (market, language, models), site tracking and CMS status, brand voice, and Content Studio skills. Use it to find the competitor_id and segment values other tools take, and to see the current state before changing a setting. For metrics use get_brand_overview.
Inputs: brand (required). Returns: data, generated_at, schema_version
get_brand_setupGet brand setupARead-onlyIdempotentInspect
A brand setup's progress and, once it needs approval, its proposals: the brand, competitors, segment, and prompts, each with the proposal_id approve_brand_setup takes.
Inputs: setup_id (required). Returns: data, generated_at, schema_version
get_citation_sourceGet citation sourceARead-onlyIdempotentInspect
One cited source. With domain: its citations, models, brands named, trend, and its most influential pages. With source_id: one page's citing prompts, models, brands named, recent snippets, and trend.
Inputs: brand (required), to, from, domain, +1 more. Returns: data, generated_at, schema_version
get_docGet docARead-onlyIdempotentInspect
Fetch one public Cleotic documentation page by slug. Links inside a page are slugs this tool takes. Use search_docs first when you have no slug.
Inputs: slug (required). Returns: data, generated_at, schema_version
get_narrativeGet narrativeARead-onlyIdempotentInspect
One reputation narrative from get_reputation: the questions it appears in, the latest quotes per engine with answer IDs for get_answer, its alerts, and any decision a person made on it.
Inputs: brand (required), narrative_id (required). Returns: data, generated_at, schema_version
get_operationGet operationARead-onlyIdempotentInspect
Follow a write: its live status (pending, completed, or failed) read from the resource itself, its progress, and how long to wait before checking again. Only the member and connection that made the write can read it.
Inputs: operation_id (required). Returns: data, generated_at, schema_version
get_opportunityGet opportunityARead-onlyIdempotentInspect
One opportunity with its evidence (who is winning, verbatim excerpts, cited sources, trend), its play and the tool call that carries it out, before/after proof, timeline, and comments. Content gaps include each engine's latest answer. Read it before act_on_opportunity or create_page; to browse the inbox use list_opportunities.
Inputs: brand (required), opportunity_id (required). Returns: data, generated_at, schema_version
get_pageGet pageARead-onlyIdempotentInspect
One Content Studio page: its brief (goal, reader, angle), target questions, outline, the page as Markdown (in parts when long), the latest conversation with Cleotic's page agent including any question it is waiting on, its pending suggestions and authority notes, and results once live. Read it after create_page and message_page; to find pages use list_pages.
Inputs: brand (required), page_id (required), cursor. Returns: data, generated_at, schema_version
get_perceptionGet perceptionARead-onlyIdempotentInspect
How AI answers describe the brand and its competitors: scores out of 10 on each dimension, by model, with the brand's evidence quotes and trend. Only analysis inside the period is used; has_data is false when there is none, and latest_analysis_at then says which period to ask for. Competitors are capped, best score first. Not included on every plan. For what answers claim about the brand, use get_reputation.
Inputs: brand (required), to, from, max_competitors. Returns: data, generated_at, schema_version
get_planGet planARead-onlyIdempotentInspect
Read the organisation's plan: limits and their use (null limit = unlimited), included features, the Content Studio allowance, the model budget, and the AI models every segment collects from. Check it before a write that costs plan capacity, a generation, or model budget.
Inputs: no named parameters. Returns: data, generated_at, schema_version
get_readinessGet site readinessARead-onlyIdempotentInspect
The brand site's AI readiness scan. view summary: score, verdict, lens and pillar scores, and open findings by severity. view action_plan: open findings to fix, with the questions no page answers. view pages: pages the scan read, or with page_id one page's open findings. view history: past scans. view competitors: competitor scans, the checks they pass that the brand fails, and the plan's competitor limit and cooldown; competitor scans are started in the app, not through MCP.
Inputs: brand (required), sort, view, limit, +5 more. Returns: data, generated_at, schema_version
get_readiness_findingGet readiness findingARead-onlyIdempotentInspect
One readiness check: why it matters, its drafted fix, and where it fails. Pass check_request_id to follow a verify_readiness_fix re-check.
Inputs: brand (required), check_id (required), limit, cursor, +2 more. Returns: data, generated_at, schema_version
get_reputationGet reputationARead-onlyIdempotentInspect
What AI answers claim about the brand: open narratives (repeated claims grouped into one story) with severity, state, the engines carrying each as "k of n" answers, first sighting, a quote, the confirmed fact it contradicts and the top cited source, plus exposure: how many answers naming the brand carried a risky claim. Strengths are listed apart. Use get_narrative for one narrative's answers.
Inputs: brand (required). Returns: data, generated_at, schema_version
list_answersList answersARead-onlyIdempotentInspect
AI answers, newest first. With prompt_id: that prompt's answers across models, with the brands they mention and recommend. Without: answers that mention the brand, with the mention in context; empty for a brand no answer mentions, while prompt_id shows a prompt's answers either way.
Inputs: brand (required), to, from, limit, +4 more. Returns: data, generated_at, schema_version
list_brandsList brandsARead-onlyIdempotentInspect
List the brands and studies you can access, with visibility, share of voice and recommendation (each with the answers and models behind it and its change on the previous period), citations, site readiness, collection health, AI traffic, and the opportunity inbox's Now stage. Brands come in name order, so paging stays steady as brands are added. Start here to find a brand ID.
Inputs: to, from, kind, limit, +1 more. Returns: data, generated_at, schema_version
list_citationsList citationsARead-onlyIdempotentInspect
The sources AI answers cite for this brand's prompts. view overview: totals by ownership and source type, by week. view domains: cited domains, with source gaps where competitors are cited and the brand is not. view pages: cited pages ranked by influence. Only domains and pages are paged.
Inputs: brand (required), to, from, view, +6 more. Returns: data, generated_at, schema_version
list_opportunitiesList opportunitiesARead-onlyIdempotentInspect
The brand's opportunity inbox: content, readiness, source, traffic, and coverage gaps, each with its score, AI search demand, stage (now, in_flight, watching, won), and assignee, plus stage counts for the active inbox (counts.ready_to_win: watching items whose gap has closed). Start here to find an opportunity_id, read it with get_opportunity, and change it with act_on_opportunity or update_opportunities.
Inputs: brand (required), kind, view, limit, +4 more. Returns: data, generated_at, schema_version
list_pagesList pagesARead-onlyIdempotentInspect
The brand's Content Studio pages, newest first, with their status: drafting, sent (to the CMS as a draft), live (locked, with results tracked) or revising. Start here to find a page_id for get_page.
Inputs: brand (required), limit, cursor, status. Returns: data, generated_at, schema_version
list_promptsList promptsARead-onlyIdempotentInspect
The brand's tracked prompts, highest AI search demand first, with segment, status, labels, monthly AI searches, and how many answers in the period mentioned the brand. Use it to find a prompt_id for list_answers; suggest_prompts proposes new prompts and save_prompt adds them.
Inputs: brand (required), to, from, limit, +3 more. Returns: data, generated_at, schema_version
list_reportsList reportsARead-onlyIdempotentInspect
The brand's saved reports, with their date ranges and public share links. Use it to find a report to revoke_report; create_report makes a new one.
Inputs: brand (required). Returns: data, generated_at, schema_version
mark_page_publishedMark page publishedAInspect
Record that a page is live at a URL, for pages published outside a connected CMS. The page locks, and Cleotic compares answers to its target questions from that day. Free.
Inputs: url (required), brand (required), page_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
message_pageMessage pageAInspect
Talk to a page's agent as you: answer its question, ask for a change, approve its outline, or ask why something is the way it is. The agent replies, and may edit the page or the brief. Returns pending while it works; read the reply with get_page. Cost: model budget; the first draft of a page uses one Content Studio page.
Inputs: text (required), brand (required), page_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
revise_pageRevise pageBInspect
Unlock a live page for changes. Results keep counting from when it first went live; send or publish the new version when it's ready. Free.
Inputs: brand (required), page_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
revoke_reportRevoke reportADestructiveInspect
Kill a report's public link. A revoked link stays dead: it cannot be restored, so create_report makes a new report with a new link. The report stays listed with revoked: true. Free.
Inputs: brand (required), report_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
run_readiness_scanRun readiness scanAInspect
Start a full site readiness scan of the brand's website. Owners and admins only. Only the first scan, or a retry while none has completed, can be started by hand; later scans run weekly, and the call is then refused with scheduled_only and next_run_at (get_readiness shows can_start_scan). verify_readiness_fix re-checks one issue. Returns pending; follow it with get_operation or get_readiness. Cost: one full scan, counted for the month; scans have no monthly allowance.
Inputs: brand (required), idempotency_key (required). Returns: data, generated_at, schema_version
save_competitorSave competitorAInspect
Add a competitor, or with competitor_id edit one or pause and resume tracking it. A change to how answers name it re-reads existing answers automatically; it returns pending until that finishes. Cost: a new competitor is one tracked brand of plan capacity.
Inputs: brand (required), idempotency_key (required), name, domain, +3 more. Returns: data, generated_at, schema_version
save_factSave factAInspect
Add a fact to the brand's fact library, or with fact_id edit, confirm or reject one. Set from_user only when the user told you the fact in this conversation; it is then confirmed as theirs. A fact you found yourself, on their site, the web or a draft, is proposed with its source_url and waits for the user to confirm it. The same fact is stored once. Free.
Inputs: brand (required), idempotency_key (required), kind, text, +7 more. Returns: data, generated_at, schema_version
save_promptSave promptAInspect
Add a prompt to a segment, or with prompt_id edit one. Changing an existing prompt's text replaces it, keeping the old prompt's answers in its history. Cost: an active prompt is plan capacity; new and replaced prompts get a first answer from every model, using model budget.
Inputs: brand (required), idempotency_key (required), tags, text, +9 more. Returns: data, generated_at, schema_version
save_segmentSave segmentAInspect
Add a segment (a market and language to track), or with segment edit one or pause and resume it. A segment can carry an audience on the Business plan: a buyer described by situation (budget, role, company size, home, priorities) that is sent with every prompt as an 'About me' line, so answers show what the engines tell that buyer; Google AI Overviews and AI Mode are not collected for it. To compare an audience with an existing segment, create a new segment with copy_prompts_from and an audience. Cost: an active segment is plan capacity and collects daily from every plan model, using model budget; copied prompts each use one prompt of plan capacity.
Inputs: brand (required), idempotency_key (required), geo, name, +7 more. Returns: data, generated_at, schema_version
search_docsSearch docsARead-onlyIdempotentInspect
Search the public Cleotic documentation by keyword and return matching pages. Use it when you do not know which page you need; use get_doc when you already have a slug.
Inputs: query (required), limit. Returns: data, generated_at, schema_version
search_factsSearch factsARead-onlyIdempotentInspect
The brand's fact library: what the brand stands behind (confirmed) and facts found on its site, the web or a draft that wait for the brand to confirm them (proposed). With query, the best matches by words and meaning; without, every fact except contact details, proposed first. Quote only confirmed facts as the brand's own and check stale ones with the user first. Add, confirm or reject facts with save_fact.
Inputs: brand (required), limit, query, cursor, +2 more. Returns: data, generated_at, schema_version
search_siteSearch siteARead-onlyIdempotentInspect
Passages from the brand's own website that match a query, by words and meaning, with the page each comes from. Cleotic reads the pages its latest site readiness scan found, up to 100, after each scan. Use it to see what the site already says before asking the user, and quote it as the site's wording. index says when the site was last read.
Inputs: brand (required), query (required), limit, cursor. Returns: data, generated_at, schema_version
send_page_to_cmsSend page to CMSAInspect
Send the page to the brand's connected CMS as a new draft, never published: the team publishes it there, and Cleotic marks the page live when it sees it on the site. Needs exactly one ready CMS destination; otherwise send it from the app. Confirm with the user first. Free.
Inputs: brand (required), page_id (required), idempotency_key (required). Returns: data, generated_at, schema_version
set_primary_brandSet primary brandAInspect
Create or edit the brand being tracked: its name, domain, and aliases. Pass at least one; what you leave out stays as it is. To add a competitor use save_competitor; to rename a brand or study, or pause it, use update_brand. A change to how answers name the brand re-reads existing answers automatically; it returns pending until that finishes. Free.
Inputs: brand (required), idempotency_key (required), name, domain, +1 more. Returns: data, generated_at, schema_version
start_brand_setupStart brand setupAInspect
Add a brand the way the app does: Cleotic reads the website and proposes the brand, competitors, a segment, and prompts. Returns pending while it reads; poll get_brand_setup until it needs approval, review the proposals with the user, then approve_brand_setup. Cost: model budget to read the site.
Inputs: url (required), idempotency_key (required). Returns: data, generated_at, schema_version
suggest_promptsSuggest promptsARead-onlyIdempotentInspect
Suggest prompts for a segment about a topic. Ranked by AI search demand only when the demand provider has data; monthly_ai_searches null or 0 means none was found. Saves nothing and returns no IDs: add the ones you want with save_prompt (text, tags, category, intent_type). Cost: one AI model call from the model budget.
Inputs: brand (required), topic (required), segment (required), count. Returns: data, generated_at, schema_version
update_brandUpdate brandAInspect
Rename a brand or study, or pause or resume it. Cost: resuming restarts daily collection, which uses plan capacity and model budget.
Inputs: brand (required), idempotency_key (required), name, status. Returns: data, generated_at, schema_version
update_brand_voiceUpdate brand voiceAInspect
Set the default tone for the brand's Content Studio pages, or none to clear it. The page agent writes in it from its next turn; pages already written are not rewritten.
Inputs: tone (required), brand (required), idempotency_key (required). Returns: data, generated_at, schema_version
update_opportunitiesUpdate opportunitiesAInspect
Triage inbox opportunities: move one or more to a stage, assign, snooze, dismiss, or restore them. All listed opportunities change together or none do. To record a play that was done, such as a fix shipped or outreach sent, use act_on_opportunity instead.
Inputs: brand (required), idempotency_key (required), opportunity_ids (required), stage, +5 more. Returns: data, generated_at, schema_version
verify_readiness_fixVerify readiness fixAInspect
Re-check a fix without a full scan. With opportunity_id, re-checks an inbox readiness task; the result updates the task. With check_id, re-checks that open finding on its affected pages. Returns pending with the re-check's id; follow it with get_operation or get_readiness_finding's check_request_id. Cost: by opportunity_id free, once every 10 minutes; by check_id one of the plan's monthly re-checks.
Inputs: brand (required), idempotency_key (required), check_id, opportunity_id. Returns: data, generated_at, schema_version
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI visibility analytics for brand mentions, citations, sentiment, and GEO reports
Track how ChatGPT, Gemini & Perplexity mention, rank & cite your brand. AuraCite account required.
AI search visibility: brand mentions, citations, rankings, competitors and top cited sources.
Track how ChatGPT, Claude, Perplexity and other AI assistants mention your brand, right from your AI client.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables AI agents to check brand mentions across AI search surfaces like ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews using natural language queries.414 npm1MIT
- AlicenseAqualityBmaintenanceAI visibility and SEO data for AI agents. Check whether ChatGPT, Claude, Perplexity and Gemini mention your brand and which sources they cite, plus keyword volume and Google Trends.29943 npm1MIT

LLM Pulse MCP Serverofficial
AlicenseAqualityCmaintenanceMonitors brand mentions, citations, sentiment, competitor share of voice, and GEO performance across AI search engines.1MIT- AlicenseNot gradedqualityCmaintenanceEnables auditing and monitoring brand visibility, citations, and competitor share-of-voice across ChatGPT, Perplexity, Claude, Gemini, and DeepSeek from MCP-compatible clients such as Cursor and Claude Desktop.9 npm35MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.