AdVizion
MCP server: live
AI assistants such as Claude, ChatGPT, Cursor, and VS Code connect to this address. A web browser can't use it directly, so you are seeing this page instead.
https://www.advizion.ai/mcp
Paste that address into your assistant as a remote MCP server, then sign in to AdVizion when it asks. Step-by-step setup for each assistant is in the API and MCP documentation.
What an assistant can do after you sign in
get_profile— Return the AdVizion account connected to this client.list_projects— List projects this account can open. Start here to get a project_id.get_project_context— Return the campaign objective, audience, and applicable rulebooks for one accessible project.list_creatives— List the creatives saved in a project with their latest version id. Use latest_version_id as creative_version_id when quoting or starting an analysis.quote_analysis— Report the credit cost of analyzing one image, video, or audio creative. This does not start work. With a creative_version_id, an earlier identical analysis is reused at no cost.start_analysis— Start a real AdVizion analysis of one saved creative version and return the review id. It spends credits, never more than max_credits; call quote_analysis first. Reusing the same idempotency_key returns the same review. Poll get_analysis_status for the RUN, FIX, or REJECT verdict. A verdict is not human approval.get_analysis_status— Return the status of an analysis this account can see, and each item's RUN, FIX, or REJECT verdict once its Decision Report exists. Read the full report with get_analysis_report.get_analysis_report— Return one stored Decision Report: the RUN, FIX, or REJECT verdict, why, the evidence-anchored findings, placements, governance status, approval state, and a link to open it in AdVizion. Use the decision_report_id from get_analysis_status. Attention values are model predictions, not eye tracking.submit_for_review— Save a Decision Report's recommendation into AdVizion's approval workflow so a person approves or requests changes. It moves a draft (or a report sent back for changes) to waiting for review; calling it again changes nothing. It never approves, rejects, or publishes.get_brand_rulebook— List the rulebooks that apply to a project, including status and version.run_governance_check— Check a project, or one creative version in it, against one active rulebook. The verdict is automated. It is not legal clearance.list_campaigns— List campaigns this account can open (the same ids as list_projects). Start here to get a campaign_id.get_campaign_context— Return the objective, audience, market and applicable rulebooks for one campaign.get_campaign_plan— Where, when, and how & how much to run a reviewed ad: three decisions with reasons, sources and a confidence level (evidence support, never a promise of results). Reading never builds a plan.get_market_brief— The dated, sourced market research behind a report's Campaign Plan: season, news, competitors and the calendar.replan_campaign— Ask for a fresh Campaign Plan for a report (free, a few per campaign per day). It takes about a minute; read it with get_campaign_plan.list_guard_proposals— Actions AdVizion suggests on live Google Ads and Meta campaigns (such as pausing an ad that missed its target) that wait for the owner's OK.approve_guard_proposal— Approve one action AdVizion suggested on a live campaign, for the account owner. It only approves AdVizion's own proposal; it never sets amounts or launches anything. Needs the advizion.campaigns.manage permission.dismiss_guard_proposal— Dismiss one suggested action and keep the campaign as it is. Needs the advizion.campaigns.manage permission.set_guard_mode— For a launch AdVizion already protects, choose what happens when it misses the owner's target: ask_first (a one-click proposal) or pause_on_its_own. Spend limits always pause at once. It never changes targets or budgets and never runs a campaign. Needs the advizion.campaigns.manage permission.compare_creatives— Compare two stored Decision Report verdicts for a stated objective. This does not invent a new score.
RUN, FIX, and REJECT are recommendations. They are not approval to publish a campaign.