Bring your AI visibility into Cursor, Claude Code, Codex and ChatGPT
GEO Tracker AI has an existing advanced Model Context Protocol server at /api/mcp for authenticated client setups. A separate public OpenAI read-only plugin is being prepared at /mcp; it is not yet available to connect.
- Existing advanced endpoint uses Streamable HTTP
- Existing advanced endpoint: OAuth 2.1 and PAT client setup
- 10 advanced legacy tools; planned public v1 has 5 read-only tools
- Pro+ feature — included at $129/mo
One-click install opens Cursor and pre-populates ~/.cursor/mcp.json — you still paste your token into the dialog after issuing one. Not on Cursor? Use the fallback block below or jump to the per-client snippets.
Show fallback JSON (paste into any client's mcp.json)
{
"mcpServers": {
"geo-tracker-ai": {
"url": "https://geotrackerai.com/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Public OpenAI plugin v1 — in development
A separate read-only endpoint is being prepared for ChatGPT and Codex
The planned public endpoint is https://geotrackerai.com/mcp. It has a deliberately narrow five-tool read-only catalog for stored evidence. It does not start scans, consume credits, create or edit GEO Tracker data, contact third parties, or make an external placement claim.
This is deployment-ready code under local validation, not a public production connection. It has not been deployed, submitted to OpenAI, approved, or published. Do not add this endpoint to a client yet.
Existing advanced integrations continue to use /api/mcp with their established authentication and tool catalog. The public v1 endpoint will use OAuth 2.1 and the mcp:read scope after production and OpenAI review gates are independently complete.
list_projectsLists owned projects so you can select the right stored visibility evidence.
"List my GEO Tracker projects so I can choose one."
get_visibility_summaryReturns the latest stored score, comparison, evidence state, and engine breakdown for one owned project.
"Show the stored visibility summary for my selected project."
compare_competitorsCompares measured customer and competitor visibility for one owned project.
"Compare my selected project with the leading measured competitor."
get_prompt_gapsShows stored prompts that are missing, weak, or led by competitors.
"Show the measured prompt gaps for my selected project."
get_citation_opportunitiesShows stored citation-source opportunities without outreach or placement claims.
"Identify measured citation opportunities for my selected project."
Existing advanced endpoint
Three steps for the existing legacy MCP connection
Issue a token
Open Settings → Integrations → MCP and click "Issue token". You name it (e.g. "Cursor on M1") and pick an expiry. The cleartext token is shown exactly once — copy it now.
Add the server to your client
Paste the per-client snippet into the right config file. Cursor uses ~/.cursor/mcp.json, Claude Code uses `claude mcp add`, Claude Desktop uses Settings → Connectors. Full snippets below.
Ask your AI
Restart the client and prompt it: "What's my current AI Visibility Score?" or "Where are my competitors being cited that I'm not?" Your AI picks the right MCP tool and answers with live data.
OAuth — existing advanced endpoint
One-click connect via OAuth 2.1
The existing advanced endpoint supports OAuth 2.1 and Dynamic Client Registration. This legacy setup information is separate from the in-development public OpenAI plugin and does not prove its availability in a client marketplace.
If a compatible client offers an OAuth connection for this endpoint, its connection flow can redirect you to the GEO Tracker consent screen. Confirm the client's current connection support and setup requirements in its official documentation; no marketplace listing availability is implied here.
What gets granted
- Read your visibility data — GEO scores, tracked questions, citation gaps, competitor analysis, weekly trends.
- Run scans and modify tracked questions (optional) — burns scan credits, can flip dashboard actions to done.
Revoke access
Settings → Integrations → Connected apps → Revoke. The next call from that app returns 401 immediately — the IDE will walk through consent again to reconnect.
Flow: Cursor → Click Connect → geotrackerai.com consent screen → Approve → access granted, no PAT paste needed.
For the manual PAT path (older clients or scripts), see the install tabs below.
Legacy install snippets
Paste-ready config for the existing advanced endpoint
Each snippet uses the placeholder <YOUR_TOKEN> — issue one from Settings → Integrations → MCP and substitute it (or export it as $GEO_TRACKER_TOKEN so the env-var placeholders resolve).
Paste into ~/.cursor/mcp.json (or .cursor/mcp.json in a project). Export GEO_TRACKER_TOKEN before launching Cursor, then restart.
{
"mcpServers": {
"geo-tracker-ai": {
"url": "https://geotrackerai.com/api/mcp",
"headers": {
"Authorization": "Bearer ${env:GEO_TRACKER_TOKEN}"
}
}
}
}Advanced legacy tool catalog
10 tools on the existing /api/mcp endpoint
This catalog is separate from the planned public OpenAI read-only v1 above. Your client decides when to invoke each legacy tool; write tools remain subject to their usual product permissions and budgets.
get_geo_scoreReturns the current GEO Score (AI Visibility Score) for the connected domain along with per-engine breakdown.
"What is my current AI visibility score and which engine is dragging it down?"
list_questionsLists tracked questions with their confidence bucket, mention rate, and last-scan timestamp. Supports filtering by bucket.
"Show me my Verified questions where mention rate dropped this week."
add_tracked_questionAdds a new question to the tracked set. Respects the stored-queries tier cap and runs Confidence Coach on the new question.
"Track the question 'best AI visibility tracker for SaaS' on my domain."
get_citation_gapsReturns the top citation gaps — questions where competitors are cited but you are not, with the cited domain URLs.
"Where are my competitors being cited that I am not? Give me 5 gaps with content angles."
get_competitor_diffCompares your AI Share of Voice vs. each tracked competitor over the last 30 days.
"How is my SoV trending against Profound and Otterly over the past month?"
suggest_content_briefGenerates a content brief for a citation gap — the angle, the headers to cover, and which AI engines reward which sources.
"Draft a brief I can hand to my writer for the 'Cursor MCP setup' gap."
get_top_actionsReturns the unified Playbook — top pending actions ranked by predicted GEO-score lift × effort.
"What are the 3 highest-leverage things I should ship this week?"
mark_action_doneMarks an action as done. Triggers the 14-day Outcome Loop measurement so you can attribute lift later.
"Mark action #a47 as done — I just shipped the comparison page."
run_manual_scanTriggers an on-demand scan of one or more tracked questions against your tier-eligible AI engines. Consumes from the manual-scan budget.
"Re-scan the questions tagged 'pricing' against ChatGPT and Perplexity right now."
get_visibility_trendReturns the daily GEO Score trace plus mention-rate deltas for the last 30 / 60 / 90 days.
"Plot my GEO Score for the last 30 days and call out any week with >5pt movement.”
Get started
Ready to wire it up?
Pro tier and above — 14-day trial on Pro Monthly
The MCP server, manual scans, Confidence Coach and Citation Why all unlock together at Pro. If you are already on Pro+ you can issue your first token from Settings now.
FAQ
The honest answers
Is my data shared with the AI client I connect?
Yes — anything the MCP tools return becomes visible to whichever AI client you connected (Cursor, Claude Code, ChatGPT, etc.). The MCP server only exposes data your own account can see; it never reveals other customers, internal usage analytics, or billing details. Treat the connection like inviting that AI vendor into your dashboard read-only, plus the ability to trigger scans on your behalf.
How do I revoke a token?
Open Settings → Integrations → MCP, find the token in the active list, and click Revoke. The change is immediate — the next call from that token returns 401. Revoked rows stay visible (with a "Revoked" badge) so you have an audit trail of which clients were connected when.
Can I use this on the Free tier?
No. The MCP server is Pro+ (Pro, Business and Scale). Free and Starter accounts still see the Integrations card, but issuing a token returns an upgrade prompt. We gate this because real MCP usage triggers manual scans and reads paid-tier surfaces (Citation Why, Competitor Diff, Visibility Trend) that are not in the Free or Starter feature matrix.
What if my token leaks?
Revoke it immediately from the active tokens list and issue a new one with a fresh name (e.g. "Cursor on macbook — rotated May 21"). MCP tokens cannot change billing settings or delete domains — but they can read your data and consume your manual-scan budget, so rotation is the right reflex if the token ends up in a git diff, a screenshot, or a shared shell history.
Which AI clients are supported today?
This page documents the existing advanced /api/mcp endpoint for authenticated client configuration. The separate public OpenAI plugin endpoint at /mcp is still in development and is not yet a production connection or a submitted, approved, or published ChatGPT app. Verify the current client configuration in its official documentation before connecting.
Does running tools through MCP count against my scan limits?
The planned public OpenAI v1 is read-only and does not run scans or consume credits. The existing advanced endpoint has its own documented tier, permission, and budget rules; check the legacy catalog and your dashboard before using an advanced action.