What can I export, and from where?
| Data | Where | Format |
|---|---|---|
| Sampled answers | AI Visibility, Export N sampled answers in the report header | CSV |
| Citations | AI Visibility, Citations tab, Export N citations in the header | CSV |
| Tracked prompts and their results | Prompts tab, export menu | CSV or JSON, download or copy |
| Engine searches | Prompts tab, Engine searches, export menu | CSV or JSON |
| Your pages | Websites, the pages list | CSV |
| AI crawler visits | AI Traffic Analytics | CSV |
How do I export every answer for a period?
- Open AI Visibility for the brand.
- Pick the date range in the toolbar.
- Click Export N sampled answers, where N is the number of answers in the range.
- The CSV downloads with one row per answer, in the columns the server defines, so a new column is never dropped.
One file holds up to 20,000 rows. If a range holds more, the app says it exported the first 20,000, so a file never quietly contains less than the button promised. Empty cells mean no observation exists, never zero.
Can I export citation data for reporting?
Yes. The Citations tab exports every cited page in the range as CSV, ready for a spreadsheet or a BI tool, and on paid plans our team can set up a feed into Looker Studio or the BI tool you already use. For a page a client or a boss can open without an account, use Share Report instead, described in Integrations and reporting.
Is there a REST API?
Yes. The Reports API at api.proofsource.co/v2 returns your data as JSON: /v2/reports/visibility, /v2/reports/citations, /v2/reports/sentiment and /v2/reports/fanouts, authenticated with an API key from Settings. Its OpenAPI spec is published at api.proofsource.co/v2/openapi.json, so you can generate a client in any language.
Can my own AI agent read my data?
Yes, over the Model Context Protocol (MCP). An AI agent such as Claude Code, Claude Desktop, Cursor or one built on the OpenAI API reads the same numbers you see in the app, from the server at mcp.proofsource.co/mcp.
- In the app, open Settings, then API Keys, and create a key. Copy it straight away: it is shown only once.
- Choose read for an agent that only looks. Choose write only if it should also add questions or mark fixes shipped. A key acts with your role in the workspace.
- Open Settings, then AI agents, copy the server URL and the setup snippet for your client, and paste your key where it says.
| Tool | What it returns or does |
|---|---|
| list_brands | Your tracked brands and their ids. |
| list_topics | Topics and the buyer questions tracked under each. |
| get_visibility | How often AI answers mention you, by engine or by question. |
| get_competitors | Share of voice against the competitors AI answers name. |
| get_citations | The sources AI answers cite, and where your domains rank. |
| get_citation_pages | The exact pages AI answers cite, which engines cite them and whether they name you. |
| get_answers | The text of AI answers to your buyer questions, or one answer in full with its sources. |
| get_changes | What moved: visibility trend, answer churn, competitor site changes, new sources. |
| query_today_alerts | Problems new since yesterday, as the Today screen shows them. |
| query_competitor_gaps | Questions where AI names your competitors but not you. |
| query_competitor_changes | What competitors changed on their watched pages: pricing, features, positioning. |
| query_sentiment_themes | How AI answers speak about you and your competitors, theme by theme. |
| list_fix_opportunities | Your gap register: what keeps engines from citing you, and the fix. |
| get_fix_verification | Each shipped fix's before and after, and whether it worked. |
| query_results | Your fixes as the Results screen shows them, with each verdict. |
| get_loop | Every step from question tracked to fix checked, oldest first. |
| get_scan_status | How far a brand's first scan has got. |
| get_report_link | The share link to your newest report. |
| get_reports | Your reports, their links and how often each was opened, plus your report schedules. |
| Tool | What it returns or does |
|---|---|
| brand_data_catalog | Every data set Proofsource holds for the brand, what is connected and the date of its newest data. |
| get_credits | Credits left, this period's use and the latest charges. |
| get_site_traffic | Visits AI assistants sent to your site, and the pages they land on. |
| get_ai_referrals | Visits from each AI assistant over time, and how they move with your visibility. |
| get_search_queries | Your Search Console clicks, impressions, position and top queries. |
| get_bing_search | Bing search clicks and top queries, and Copilot citations. |
| get_ai_crawler_visits | Which AI crawlers visit your site, and which ones your site blocks. |
| get_store_products | Your store's products, and whether AI engines name each one. |
| get_store_feed_readiness | Whether your store's product feeds are ready for AI shopping. |
| get_shopping_answers | How often AI names you when its answers turn into shopping. |
| get_shopping_answer_sources | The sites AI shopping answers send buyers to. |
| get_shopping_answer_products | Your product pages, and how often AI shopping answers cite each one. |
| get_shopping_questions | Which of your buyer questions turn into shopping answers. |
| get_linkedin_posts | Your LinkedIn posts and how they did, plus drafts waiting to go out. |
| get_reviews | Your rating on each review site next to your competitors', with the date it was read. |
| get_ai_profiles | Your profiles on the business listings AI engines read, and the next step for each. |
| get_pages | Your own pages: pages tracked since a fix, and your full page list. |
| get_pages_for_question | Your pages that already cover one buyer question. |
| get_brand_facts | Your brand's key facts, and which ones your team confirmed. |
| get_ads | Who pays to appear next to the answers you lose, and how your own campaigns did. |
get_site_traffic, get_ai_referrals and get_search_queries also need the brand's switch "Let connected AI assistants read Google Analytics and Search Console", in Settings, then Connect AI apps.
| Tool | What it returns or does |
|---|---|
| find_actions | Finds the app actions that do what you ask. |
| propose_action | Shows exactly what an action will change. Nothing changes yet. |
| confirm_action | Makes the proposed change, once, after you say yes. |
| app_action | Does what a button in the app does: add a competitor, build a report, scan again at the Basic, Standard or Advanced level, and more. In agency workspaces it also sends a first pitch. |
| add_brand | Adds a brand from its website or link and starts its first scan. |
| create_prompt | Track a new buyer question. |
| mark_fix_shipped | Date a fix so Proofsource can verify it. |
| create_mission | Plans a fix for one goal, and starts it only after you say yes. |
| get_mission | A fix's steps, the step waiting for your OK, and where its proof stands. |
| post_to_linkedin | Queues a drafted LinkedIn post for a person to post. It never posts by itself. |
| Tool | What it returns or does |
|---|---|
| get_leads | Saved leads to pitch at this brand, with their stage and last email. |
| get_pitches | Your pitch to this brand, or every prospect you are pitching, with its status. |
| get_inbox | Replies and drafts waiting in your Inbox, and the emails in one thread. |
| get_calls | Calls booked with this brand's people, and the next one. |
Each key can make 60 tool calls a minute and 30 writes an hour. ChatGPT, Claude, Grok and Cursor connect without a key: you sign in to Proofsource instead, as Use Proofsource in ChatGPT, Claude, Grok and Cursor describes.