AI visibility MCP server: free on every Limelit account

Limelit's MCP server lets your AI agent read your AI visibility data without leaving the chat, and it is free on every account. It works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and ChatGPT.

Where it connects

Clients that take a personal API key connect to https://api.limelit.co/mcp.
ChatGPT connects through the Limelit app at https://limelit.co/mcp/apps.
The connection steps and your personal key are in Settings once you sign in.

208 tools

Reading your data is free. Tools that start runs or write drafts spend credits, so check a tool's cost before you call it.

actions

create_factcheck_plan_action: Create an owner-attributed pending Plan draft from exact FactCheck evidence; this never approves, publishes, sends, or performs remote writes.
decide_factcheck_plan_action: Record an explicit owner approve or discard decision for a pending FactCheck draft; approval only queues internal Plan work and never publishes or sends.
get_factcheck_plan_action: Return one tenant-owned approval draft and the exact immutable FactCheck evidence rendered by its Plan review URL.
create_owned_page_plan_action: Create an owner-attributed pending Plan draft from current Owned Pages evidence; this never approves, publishes, sends, or performs remote writes.
decide_owned_page_plan_action: Record an explicit owner approve or discard decision for a pending Owned Pages draft; approval only queues internal Plan work and never publishes or sends.
get_owned_page_plan_action: Return one tenant-owned Owned Pages approval draft with its exact page snapshot and immutable evidence references.

admin

list_org_members: OWNER ONLY.
set_spending_caps: OWNER ONLY.
update_brand_identity: OWNER ONLY.

agentic

get_agent_visits: Return crawler visit totals, active bots, failure rate, and chronological activity buckets.
get_crawl_citation_join: Return the canonical path join between AI-crawler visits and owned answer citations.
ingest_agent_log_batch: Send a batch of server request-log entries to one of your webhook agent-log sources, so Crawler analytics can count AI-crawler traffic.
list_bots: List AI crawler bots active for the selected tenant window and filters.
list_crawl_errors: List canonical paths with HTTP error responses, highest error count first.
create_perception_audit: Freeze the active property's previous 30 days of perception evidence into a shareable 90-day audit URL.
get_brand_shape: Get the brand-shape board: for each brand (yours and tracked competitors) and each attribute, the score AI engines attribute to it with the evidence snippets behind it.
get_matrix: Return the prompt-by-engine matrix for one explicit visibility, share-of-voice, sentiment, or position metric, over ALL measured runs.
get_perception_summary: Return visibility, share of voice, sentiment, average position, and prior-window deltas for the active property.
get_ranking_matrix: Return the brand-by-engine ranking matrix for one metric, restricted to a window and an optional Segment.
get_ranking_overview: Get the ranking overview: where the brand places against tracked competitors across the measured prompt set, for an explicit window and optional Segment.
get_sentiment_series: Return chronological own-brand or competitor sentiment buckets for the active property.
list_brand_attributes: List grouped AI-attributed brand traits with stance, engine evidence, and last-seen time.
list_misinformation: List newest own-brand negative or likely-hallucinated claims and correction-draft linkage.
show_share_of_voice: Show an interactive share-of-voice chart for the active brand and tracked competitors.

agents

decide_approval: Record a human accept / edit / discard on a pending approval.
list_approvals: List write-posture approvals awaiting a human decision (the Act inbox, filtered to agent-originated writes).
cancel_block_run: Request tenant-user cancellation of one queued or running workflow.
dry_run_block: Estimate credits and enumerate writes for a published block without spending or executing.
get_block_run: Get one tenant workflow run with audit events, node receipts, and evidence.
list_block_runs: List tenant workflow runs with immutable attempt and event history.
list_block_schedules: List tenant workflow schedules, exact inputs, and enabled state.
list_blocks: List composed blocks in the active workspace, including graph, status, and version.
retry_block_run: Queue the next bounded immutable attempt for a failed workflow run.
run_block: Queue a published composed block once; write outputs remain pending human approval.
schedule_block: Create, update, or disable a recurring workflow with exact typed input.
create_brand_kit: Store a Context brand kit for the active workspace.
create_skill: Store a Context skill (a reusable instruction/persona fragment) for the active workspace.
get_brand_kit: Return one Context brand kit by id.
get_skill: Return one Context skill by id.
list_brand_kits: List the workspace's Context brand kits (voice, positioning, guardrails) that ground an agent's writes.
list_context: List the workspace grounding inventory: Knowledge Sources, brand kits, segments, and reusable skills.
list_skills: List the workspace's Context skills (reusable instruction/persona fragments an agent references).
create_agent: Register a Library agent over an already-published composed block: title, intent grouping (monitor / investigate / act), and an optional grounding policy.
define_block: Define a composed block: a typed-IO node graph persisted as a draft for the active workspace, validated as an acyclic DAG before it is stored.
get_agent: Return one agent's registry metadata (title, intent, template flag, grounding policy, and the composed block it wraps).
get_agent_ports: Return the input and output ports an agent's block declares (name, type, required), so an agent column's input_bindings and output_bindings can be wired by name instead of guessed.
list_agents: List the grounded agents in the active workspace's Library, grouped by intent (monitor / investigate / act).
run_agent: Run an agent once against one input record.
set_schedule: Irreversibly attach or update unattended recurrence for exactly one Agent or Sheet owner, or cancel future occurrences with enabled=false.
cancel_run: Cancel an Agent or Sheet run through the canonical durable workflow lifecycle.
get_run: Return one run and its produced outputs: read outputs with provenance, and write outputs that became approvals.
list_runs: List recent agent runs in the workspace, newest first, optionally scoped to one agent.
retry_run: Retry a failed or canceled Agent or Sheet run as an immutable child after revalidating live owner, feature, block revision, spend, and policy gates.
list_schedules: List Agent and Sheet recurrences with exact ownership, next occurrence, enabled state, and latest run outcome.
add_sheet_column: Add one typed column to a grid table.
add_sheet_rows: Append empty rows to a grid table (or insert them directly below after_row_id).
cancel_sheet_cell: Return one QUEUED agent cell to idle, releasing its reservation against the table's ceiling.
create_sheet: Create a table.
delete_sheet: Retire a table.
delete_sheet_column: Delete one column and every cell and run state stored against it.
delete_sheet_row: Delete one row and every cell and run state stored against it.
duplicate_sheet: Copy a table into a fresh draft named "<name> copy": its columns, rows, and user-authored cells copy; agent results, cell runs, and run history stay with the source.
duplicate_sheet_row: Copy one row's user-authored values into a new row directly below it.
estimate_sheet_chain: Price a whole chain, not one column: every stage that feeds the named column, over every row, before anything is claimed.
estimate_sheet_column: Price what running one agent column would cost, without running it.
export_sheet: Return a grid table's full contents as CSV text: a Row number, then one column per stored column in position order, agent columns printing each cell's run status.
get_sheet: Return a sheet and its per-row fan-out state.
list_sheets: List the workspace's bulk sheets, newest first (the Sheets history), so a sheet stays findable without its deep link.
move_sheet_column: Reorder one column, either one step by direction (left or right) or to a destination with before_column_id (a column uuid, or the literal "end" to place it last).
move_sheet_row: Reorder one row, either one step by direction (up or down) or to a destination with before_row_id (a row uuid, or the literal "end" to place it last).
rename_sheet: Rename a table and/or move its lifetime credit ceiling (100..25000 credits), the fence every cell admission is checked against.
run_sheet: Accept a planned sheet for durable background fan-out with server-enforced concurrency and credit caps.
run_sheet_cell: Run one agent column for one row.
run_sheet_chain: Run a whole chain from one call: every stage feeding the named column, in dependency order, admitting only the cells whose own upstreams are done for that row.
run_sheet_column: Run one agent column across every runnable row, and the columns wired to run after it.
set_sheet_cell: Write one user-authored cell value in a value column (never an agent column).
update_sheet_column: Edit one column: rename it, retype it between value kinds, replace its config (a select column's options, an agent column's run_condition), or rewire an agent column's agent and bindings.

context

create_segment: Create a saved tenant Segment using the same validation and evidence contract as REST.
delete_segment: Soft-delete one tenant-owned Segment so it no longer scopes reads.
get_segment: Return one tenant-owned Segment with current membership, exact-country evidence state, and unlocated-run disclosure.
get_segment_members: Return bounded members, exact country execution evidence, requested-country exclusions, and unlocated-run state for one segment.
list_segments: List saved segments with member counts, exact-country evidence state, and separately excluded unlocated legacy runs.

editor

add_point_of_view: Add an entry to the organization's point-of-view bank, which every generated draft draws on.
add_topic: Add a topic to the organization's content backlog.
create_brief: Start a content brief for one post.
delete_draft: Permanently delete a draft.
generate_draft: Generate a brand-new blog draft from an article URL.
get_brief: Read one content brief in full, including any edits a human made after it was created.
get_draft: Fetch the full draft (title, current_md, generated_md, source_url, status, slugs) for editing or publish review.
get_draft_structure: Check whether a draft shares its section structure with the organization's other recent drafts (the sameness check).
get_post_history: Show one published post month by month since it went live (at most the last 12 months): AI citations of its URL, Search Console clicks and impressions, and AI assistant referral visits from Google Analytics, plus the 14-days-after-publish score when one was taken.
list_briefs: List the organization's content briefs, newest first.
list_citation_drops: List published posts that AI engines cite much less than before: at least 3 citations in the previous 30 days and half or fewer in the last 30, the largest loss first.
list_drafts: List blog drafts for the active property, including status (draft / published) and the latest title.
list_landing_pages: List the organization's landing page drafts (use case, comparison and alternatives pages, as opposed to blog posts), newest first, with each one's page type, subject, title and status.
list_point_of_view: List the organization's point-of-view bank: the beliefs, contrarian takes, first-party data, expert quotes and customer stories that every generated draft draws on.
list_topics: List the organization's content topic backlog: what it plans to WRITE about (not the prompts Limelit tracks), high intent first in the team's order, each with its source, evidence, status (idea, planned, drafting, published, dropped; drafting and published come from its brief or draft) and planned week.
publish_draft: Publish a draft.
score_content_quality: Score a blog draft against the Panda content-quality rubric, the same 0-100 score and the same seven checks the editor's sidebar shows a writer: word count (25), heading structure (15), section depth (15), content variety (15), external citations (10), title quality (10; a title over 60 characters fails it, since search results cut it off), readability (10).
update_draft: Update a draft's title and / or current_md (the in-progress markdown).

evidence

get_factcheck_check: Return one tenant-owned Cross Check and its exact claim, verdict, rationale, Knowledge Source evidence, citation relationships, and reviewer override.
get_factcheck_claim: Return one tenant-owned claim using the stable REST read model and its immutable evidence identifiers.
get_factcheck_result: Read one recorded Cross Check as the automation scoreboard run_factcheck answers with: check id, effective verdict counts, accuracy rate, and per-claim rows with any reviewer override.
get_factcheck_verification: Return one durable Cross Check attempt with exact diagnostics, evidence fingerprint state, result check ID, and preserved last-good check ID.
list_factcheck_checks: List immutable Cross Check invocations for the active tenant with exact answer-run and claim-count provenance.
list_factcheck_claims: List persisted FactCheck claims for one answer run without recomputing or upgrading unsupported and not-relevant verdicts.
list_factcheck_verifications: List asynchronous Cross Check attempts for one answer, preserving queued/running/failed/succeeded and current/stale/source-deleted/empty evidence states.
run_factcheck: Run Cross Check on one saved answer run: extract its factual claims and verify each against the tenant's active Knowledge Sources, recording an immutable check.
list_knowledge_source_refreshes: List durable refresh attempts for one Knowledge Source, including persisted failure diagnostics and result version IDs without claiming failed evidence is current.
list_knowledge_source_versions: List immutable versions for one tenant-owned Knowledge Source, preserving exact version, content digest, and collection identifiers.
list_knowledge_sources: List tenant-owned Knowledge Sources with last-good version IDs, refresh health, and truthful queued/running/succeeded/failed/stale lifecycle state.
get_owned_page: Read one already-materialized tenant-owned page without identity reconciliation; includes related prompts, competing sources, answers, and action readiness.
list_owned_pages: List tenant-owned canonical pages after idempotently reconciling tenant-local identity from stored evidence; returns stable IDs and truthful evidence states with no remote side effects.

gtm

gtm_check_draft_quality: Ask the quality gate whether a draft may be published, BEFORE publishing it.
gtm_create_draft: Start a GTM blog draft.
gtm_list_drafts: List GTM drafts filtered by status (any of: generating, draft, published).
gtm_publish_draft: Publish a GTM draft.
gtm_queue_task: Enqueue an Operate Inbox task (cold_email, listicle_pitch, reply_to_thread, social_post, partnership_dm, journalist_pitch, draft_review).
gtm_score_post: Read the 14-day backpressure score for a published URL: clicks, impressions, position, CTR, pulled from the org's GSC data.

integrations

create_cms_draft: Create an awaiting-approval CMS draft; this tool cannot publish content.
list_cms_destinations: List the organization's WordPress and Webflow draft destinations and which are connected (no secrets).

overview

add_chart_note: Put a dated note on the organization's metric charts, such as a launch or a site change.
get_active_property: Return the active property (a.k.a.
get_ai_referrals: Report the visits AI assistants (ChatGPT, Perplexity, Claude, Gemini, Copilot and others) sent to the site, from the organization's connected Google Analytics 4 property: sessions and engaged sessions by assistant against the previous window, the daily series, the landing pages they arrived on, and how fresh the data is.
get_kpi_history: Get the DAILY SERIES behind the headline KPIs, so a change can be located in time instead of asserted.
get_overview_kpis: Return brand-visibility %, citation-share %, competitor + tracked-prompt counts, and the trailing-window competitor rankings + top-cited sources for the active property.
get_results: Compare the organization's AI visibility, citation share, average rank and AI referral visits since its baseline date (for example the day it started AEO) with an equal window before it, basis-weighted like the dashboard.
get_run_activity: Snapshot of in-flight + recently-completed prompt runs across the four LLM providers (ChatGPT, Claude, Perplexity, Gemini).
get_scoreboard: Get the dashboard scoreboard: the headline standing of your brand against tracked competitors as the product renders it on the home dashboard.
get_site_traffic: Report ALL visits to the site from the organization's connected Google Analytics 4 property, split into AI assistants, organic search, direct and other: sessions, engaged sessions and conversions per channel with each channel's share and change against the previous window, week by week (a week with days under 7 is partial, not a drop), and per landing page with the same split.
get_topic_metrics: Get visibility broken down BY TOPIC rather than by prompt or engine: which subject areas the brand is strong or absent in over the window.
get_weekly_digest: Get the product's own weekly digest: the deterministic at-a-glance summary of what changed for this organization, the same content the emailed digest carries.

portfolio

attach_property_to_portfolio: Attach this workspace (the organization this API key belongs to) to a portfolio you hold a portfolio membership on.
create_portfolio: Create an empty portfolio owned by you.
delete_portfolio: Permanently delete a portfolio you hold the portfolio Owner role on.
detach_property_from_portfolio: Detach this workspace (the organization this API key belongs to) from a portfolio you hold the portfolio Owner role on.
get_portfolio: Read one portfolio's summary: identity, the count of client properties you may see, and whether brands exist in it that you cannot see.
get_portfolio_auto_recharge: Read the portfolio's auto-recharge configuration: enabled, threshold, top-up amount, the hard monthly ceiling (all in credits), the banked month spend, whether a payment method is saved, and whether recharging is paused.
get_portfolio_credits: Read the portfolio's shared purse: balance in credits, a low-balance flag, and recent funding movements (top-ups and grants; never a client's consumption).
get_portfolio_rollup: Read the cross-client visibility roll-up for one portfolio: per-client visibility, basis counts, deltas, tracked prompts and last-run recency, over the clients you may see.
get_portfolio_usage: Read the per-client credit statement for one portfolio over a trailing window: per visible client, credits consumed, the split between purse-funded and self-funded, and per-feature line items, plus totals over the visible clients only.
leave_portfolio: Remove an organization you own from whatever managed portfolio it belongs to, naming no portfolio.
list_portfolios: List every portfolio you hold a portfolio membership on: id, name and timestamps only.
rename_portfolio: Rename a portfolio you hold the portfolio Owner role on.
set_portfolio_auto_recharge: Configure the portfolio's auto-recharge: enable or disable topping up the purse from the portfolio's saved card.
set_portfolio_funding: Point this workspace's metered spend at the portfolio's shared purse (funded: true) or back at its own balance (funded: false).

research

get_article: Get the per-prompt × per-platform breakdown for a specific article URL: useful before drafting a competing post.
list_articles: List articles citing the active brand or its competitors, with lifecycle (surfaced / drafting / published), per-platform counts, and helped_competitors (which competitors are also cited on the same URL).
list_top_sources: List the top-cited DOMAINS (publisher / platform / blog hosts) feeding LLM answers about the active brand, ranked by citation count.
compare_prompt_chats: Compare how every engine answered ONE tracked prompt side by side: who each engine mentioned, in what order, and which sources each one cited.
get_chat: Get ONE engine answer in full: the answer body, every brand mention with its rank position, every cited source, and the inline attribution spans when the engine provided grounding.
get_chat_facets: List the values actually present in your answer data for the window: which engines ran, which brands were mentioned, which source hosts were cited, which topics and features appeared.
list_chats: List the individual AI engine answers behind your visibility numbers, newest first, with a one-line preview, the engine, the brands mentioned and their rank positions, and the sources cited.
dismiss_suggested_competitor: Permanently dismiss a suggested brand so it stops surfacing in suggestions.
list_competitor_page_gaps: List the topics tracked competitors have a page on and the organization does not, read from each site's sitemap (each page's topic named from its URL), most competitors first, with every competitor's page on it.
list_competitors: List all currently tracked competitors for the active property.
list_dismissed_suggested_competitors: List brand suggestions that have been dismissed.
list_indirect_competitors: List company sites AI answers cited on the organization's tracked prompts in the last 90 days that it does not track as competitors (and that are not its own), most cited first: possible indirect competitors, such as products from an adjacent category buyers are pointed to instead.
list_suggested_competitors: List brand mentions that the LLM platforms have surfaced and we suspect are competitors but you haven't yet tracked or dismissed.
restore_dismissed_suggested_competitor: Undo a previous dismiss so the brand can re-surface in suggestions on the next pass.
track_competitor: Add a brand to the tracked competitors list.
untrack_competitor: Stop tracking a competitor.
get_fanout_phrases: Return recurring bigrams and trigrams from persisted fanout evidence for the active property.
get_fanouts: Return captured query fanouts for the active property, aggregated by normalized query and evidence type.
get_prompt_coverage_queries: Return the ranked sub-questions AI engines actually searched while answering one tracked prompt, strongest first.
gsc_findings: Run all six derived GSC detectors in one call: content_decay, cannibalisation, ctr_gap, quick_wins, content_gaps, traffic_drops.
gsc_property_summary: Summarise the active org's Google Search Console connection.
gsc_search_analytics: Aggregate clicks/impressions/position/CTR over the last N days for one or more URLs.
gsc_url_status: Look up the latest GSC URL Inspection result for a specific URL on the connected property.
gsc_weekly_digest: Return the weekly Google Search Console digest: top 5 quick wins, content gaps, traffic drops, and CTR gaps, plus a one-line headline.
get_search_volume: Return the monthly Google search volume for one exact phrase.
list_keyword_ideas: Return keyword ideas with monthly search volume, intent and CPC, either for a domain (what that site's market already searches for) or for a seed phrase (what shares intent with it).
get_opportunity: Get one Plan opportunity by id, with its full evidence references: which prompts and engines cited the source, which competitors it helps, and the current work state.
list_opportunities: List the Plan queue: ranked opportunities to win or defend a citation, each with its source URL, bucket (win / defend / winning), 0-100 score, proposed action, assignee, status, and the citation evidence behind it.
create_prompt: Add a new tracked prompt.
delete_prompt: Permanently delete a tracked prompt.
list_buyer_questions: List the questions, pains, objections and phrases buyers used on the organization's uploaded sales and customer call transcripts, each with the verbatim quote it came from and the call it came from.
list_call_connections: List the organization's call recorder connections (Gong, Fireflies, Zoom; no secrets): which are connected, whether an import is running, when the last import ran and what it found, plus the 20 calls imports looked at most recently with their status (read, already_read, skipped, failed).
list_prompts: List the prompts being tracked for the active property.
reevaluate_all_prompts: OWNER ONLY.
reevaluate_prompt: Evaluate one prompt again across the LLM platforms on its filter, or one engine with target.
update_prompt: Patch a tracked prompt.
get_ai_mode_answer: Return Google's AI Mode answer for a query: the answer text and the publisher sources behind it.
get_ai_overview: Return Google's AI Overview for a query: the answer text and the sources it cited.
search_serp: Run one live Google search and return the ranked organic results, the answer box, the People Also Ask questions, the related searches, and the AI Overview text when Google rendered it inline.
list_source_gaps: List the sources feeding AI answers in your category RANKED BY GAP: how often each was retrieved or cited versus how often your brand appeared alongside it.
list_source_movers: List sources whose presence CHANGED between the requested window and the window immediately before it, bucketed as top, new, trending, or losing.
compare_source_to_brand: Compare one TRACKED COMPETITOR's source presence against your own over the same prompt set: retrieved counts, cited counts, and presence ratios side by side.
get_source_overview: Get the identity and headline numbers for ONE source domain or host: what kind of source it is, how many times it was retrieved and cited in the window, whether your brand appears alongside it, and the run coverage the numbers rest on.
list_source_engines: Break one source domain or host down by AI engine: for each engine, how many distinct URLs of that source it cited and retrieved, the citation and retrieval counts, the runs that surfaced it, and runs_total, the engine's completed runs in the same window.
list_source_mentions: List the individual answers that mentioned the brand behind one source, with engine, prompt, and rank position.
list_source_prompts: List the tracked prompts whose runs surfaced one source, with per-prompt retrieved and cited counts, the engines involved, and whether YOUR brand was present in the same answer.
list_source_urls: List the individual URLs ON one source domain that AI engines retrieved or cited, ranked, with per-URL retrieved and cited counts.

sources

create_watchlist: Create a validated relationship watchlist attributed to the current user.
evaluate_watchlist: Evaluate one tenant watchlist and persist its immutable evidence snapshot.
get_source_relationships: Return one page of the prompt, answer, competitor, and action relationships around one source, in the order the Sources hub lists them.
list_watchlists: List active tenant watchlists using the same collection envelope as REST.

spend

get_automation_settings: Read which automatic, credit-spending jobs this organization turned on (for example refreshing posts that lose AI citations), each with its weekly count and weekly credit ceiling and what it used in the last 7 days.
get_spend_summary: Return today's LLM cost in cents, month-to-date cost, the configured daily + monthly budgets, per-platform breakdown for today, and a day-by-day series for the trailing window.

workflows

analyze_my_visibility: Composite digest answering 'how am I doing across LLM platforms'.
find_easy_wins: List the articles where the active brand is NOT yet cited but where ≥ 1 tracked competitor IS.
get_ai_readiness: Return the most recent AI Readiness Scan of the org's own website: how well the site is structured for AI crawlers and answer engines.
get_country_coverage: Return provider-attested AI visibility for every country represented by active geo-targeted prompts.
get_crawler_policy: Return how a site's robots.txt governs every known AI crawler and the major search engines.
get_llms_txt: Return a site's llms.txt: the curated index a publisher writes for AI assistants.
run_ai_readiness_scan: Start a fresh AI Readiness Scan of the organization's configured website domain.
suggest_my_next_blog_post: Pick the single highest-leverage article URL to write a counter-post against.
summarize_recent_activity: One-page digest of in-flight + recently-completed prompt evaluations across the four LLM platforms, with a per-platform breakdown so the agent can answer 'is anything still running' or 'why is the dashboard stale'.

Questions

The things people ask us first.

Yes. Limelit's MCP server works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and ChatGPT.

No. The MCP server is free on every account, and signup comes with 1,000 credits.

Yes. Create a free account, then follow the connection steps in Settings.

No. ChatGPT connects through the Limelit app; the other clients use a personal API key from Settings.

Yes, some do. Reading your data is free; tools that start runs or write drafts spend credits, so check a tool's cost before you call it.