Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews.
Remote server: your requests and data go to app.proofsource.co. Claude Code: claude mcp add --transport http proofsource https://app.proofsource.co/v1/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_brands — The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.list_topics — The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt nget_visibility — How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate,get_competitors — The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it chaget_citations — The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the get_changes — What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, alist_fix_opportunities — The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fixget_fix_verification — Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noiseget_loop — The brand's loop, oldest first: each buyer question tracked, gap found, content draft created, fix published to the brand's site, fix shippecreate_prompt — Adds a buyer question to a topic so it is asked on every engine in the plan from the next run. Counts toward the plan's question limit. Callmark_fix_shipped — Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measuradd_brand — Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's websiget_scan_status — Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it shget_report_link — A link to the brand's AI visibility report to share with a team or client: how often AI answers mention the brand, which competitors they nasee_example — Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.