Field guides
Connect your AI once, stop re-pasting a new snapshot every week
Guide · working with your AI
areyoufoundbyai.com/monitor/a1b2c3d4e5f60718The highlighted part is your token (that one is a made-up example). The same token works for every link on this page, and your console's Connect your AI section has all of this pre-filled with one-tap copy buttons.
Choose the connection that matches your account
- Your whole account: use
https://areyoufoundbyai.com/mcp/account, switch Requires sign-in on, and sign in. It covers your sites and the prospects you've checked. - One site: copy the private connector link from that site's console. Keep it private.
- Agency sites: create a private connection link in your console under Access and recovery (Create an AI connection), then add it to your AI as a custom connector. Keep it private.
- Connected source accounts: use
https://areyoufoundbyai.com/mcp/connectorswith Requires sign-in on, or use a current scoped key supplied by the account owner.
If a connection stops working, open your signed-in account and reconnect. A private link or key may be incorrect, expired, replaced or revoked. If a source itself needs authorization, reconnect that source in your account too. Ask the owner if your site or source is missing; never send a private link, key or password in a support message.
Agency usage tools
| Tool | Saved data returned |
|---|---|
list_site_spend | Completed checks and tokens by permitted client site. Failed and in-flight tokens stay separate. |
get_site_spend | Check records for one permitted site, with date, questions, engines, status and tokens. Completed, failed and in-progress amounts stay separate. Follow the returned next offset for more than 200 checks. |
Use period month with YYYY-MM, to_date, or custom with from and to dates. Dates use UTC. These tools cannot run checks, top up tokens or reveal the shared account balance to a scoped connection.
The button in your weekly email opens a new conversation with that week's numbers pasted in as text. Useful once, but it means every week starts from zero, no memory of what you and your AI already worked through. There's a better way, and it costs you nothing to set up: your console link is a live URL, not a snapshot. Fetched today it returns today's data; fetched again in six weeks it returns six-weeks-from-now's data, same link. Point your AI at that link once, as a standing instruction, and every new chat starts current automatically.
What to paste
Most AI chat tools let you set persistent instructions for a project or space, text applied to every new conversation inside it, not just the current one. Paste this:
Where to paste it
- Claude: create or open a Project, look for its custom instructions / project knowledge setting, and paste the text above. Every new chat inside that project starts with your latest data.
- ChatGPT: same idea inside a Project: its instructions field applies to every new chat you start there. (If you're building a custom GPT and want your AI to query this on demand mid-conversation rather than only at the start, that needs an Action wired to the JSON endpoint, more setup, ask us if you want a hand.)
- Perplexity: Spaces support custom instructions the same way; add yours to a Space dedicated to your business.
- Gemini: Gems support a persistent instructions field; create one for this and paste the text above.
Exact menu labels move around as these products update, look for "instructions," "custom instructions," or "project knowledge" inside whatever the tool calls a Project/Space/Gem. The paste-in text above is the part that matters and won't change.
Or connect over MCP, a live two-way line
The standing instruction above makes your AI read your data at the start of a chat. Your console is also a live MCP server, the open standard AI tools use to call other software, which means your assistant can query your measurements mid-conversation, whenever the question comes up, not just at the start. Your endpoint:
claude mcp add --transport http foundbyai-demo https://areyoufoundbyai.com/mcp/demoThe public demo exposes 20 tools over our own saved measurements. Your customer connection adds tools according to its permissions. These are examples of measurement tools:
get_visibility, your current AI Visibility and AI Readiness scores (each /100) with the week before for comparison, your separate off-site Footprint score, and the subscores behind them.get_question_trajectories, every tracked buyer question with its measured history, day by day: how many of the 7 engines named you each time it was asked.get_schema_evidence, the saved initial-versus-rendered structured-data comparison, including incomplete reads.get_regional_visibility, saved area and engine naming observations with retained sample coverage.get_rivals, the competitor names the engines actually gave buyers in the latest scan when they didn't name you.get_share_of_voice, your slice of AI-answer mentions against those rivals, and how it has moved over the tracked window.get_mentions, new pages on the web that mention the business, when a mention check has been run (passdaysto set the look-back window).get_context, the whole weekly picture in one call: scores, questions, mentions, fixes, the same content as the context pack above.get_fix_plan, the prioritised fix list from your latest deep scan, highest impact first.get_citation_sources, the domains the engines actually cite in your category, and whether you appear on each.get_personas, the buyer personas behind your tracked questions, with the exact questions each persona asks.get_post_brief, a drafting brief assembled from this week's verified data: fresh mentions, the questions you're absent from, the sources the engines read. Your AI writes the post, in your voice.get_ai_traffic, the visitors AI engines actually sent to your site in the last 30 days, recorded by your site's own beacon.get_agent_view, how a headless agent browser renders your site: full, partial or blank, with the characters an agent can extract.get_benchmark, where you rank against every other measured business in your category.request_rescan, a measurement request under legacy plan allowances. Token accounts use a quoted run and explicit confirmation in the owner workspace or through owner-enabled paid-run tools.
- Claude (app): Settings → Connectors → Add custom connector, paste the URL above. Then any chat can ask "what moved in my AI visibility this week?" and Claude queries it live.
- Claude Code:
claude mcp add --transport http foundbyai https://areyoufoundbyai.com/mcp/YOUR-TOKEN - Cursor: add it as a custom MCP server with HTTP transport, no API key field needed, the token in the URL is the key.
- Other MCP clients: custom server, HTTP transport, the endpoint above. The address is the whole setup.
What to ask once it's connected
Anything you'd ask a colleague who had your console open. The point of the live connection is that these work mid-conversation, weeks after setup, and always answer from this week's data:
- "What moved in my AI visibility this week, and what's the single most useful thing I can do about it?"
- "Which buyer questions am I still invisible on, and who is AI naming instead of me on those?"
- "Draft a short update for my business partner: our current scores, the trend, and any new mentions this month."
If a coding agent builds your site, the next step is Connect your AI and let it work the plan: your agent reads the fix plan over this same connection, applies the fixes in your repository with your approval, and re-measures until a target you set.
Saved measurement tools only read. Customer tools depend on the permissions the owner enables. With editing enabled, confirm_token_run can spend shared account tokens after the human agrees to a displayed quote. Owner-enabled tools can also change saved workspace content. The public demo has 20 tools and no access to a customer wallet. Read tools/list for the tools available to your connection. The same privacy rule below applies, the URL contains your token.
Keep the link private
What's actually in the data
Both formats carry the same live picture: your AI-visibility and readiness scores, the specific buyer questions engines do and don't name you for (with movement over time once you have history), the scanner's own ranked list of what to fix first, a citation game plan of where to get listed or reviewed so AI cites you, new independent mentions found in the last week, and adjacent questions worth tracking. The plain-text version at /context.md is built for attaching to a chat; the .json version is for anything that wants to parse it directly.
Still want the weekly nudge
Keep the weekly email, the new-chat button is genuinely useful the first time, or any time you want a clean-slate read. The connected project is for the ongoing conversation in between.
What does AI say about your business?
Run your free scan ↗See the answers, the competitors and the next fix.