SpritesAdd Sprites to GitHub Copilot
Available on Copilot in VS Code, and Copilot CLI. Any Copilot plan that includes agent mode. You need a Sprites account with AI visibility (AEO) already connected — the connector acts on that connection, so GitHub Copilot never handles a AEO credential.
Open the MCP configuration
Run MCP: Add Server from the Command Palette and choose Workspace or Global. Workspace writes .vscode/mcp.json, which is worth committing so the team shares the same connector; Global keeps it to you across every project.
VS CodeCommand PaletteMCP: Add ServerWorkspaceAdd Sprites as an HTTP server
The top-level key is servers, not mcpServers, and a remote endpoint needs an explicit type of http. This is the shape VS Code and Copilot share.
.vscode/mcp.json{ "servers": { "sprites": { "type": "http", "url": "https://mcp.sprites.ai/mcp" } } }Authenticate
VS Code shows an Auth action above the server entry once the file is saved. Run it, sign in to Sprites in the browser window that opens, and approve the scopes.
Spriteswants access on behalf of Copilot- Read your connected ad accounts and site data
- Draft campaigns, creatives and pages for your approval
- Apply only the changes you approve
AllowCancelSwitch Copilot Chat to agent mode
MCP tools are only offered to the agent. Pick Agent from the mode dropdown in Copilot Chat, then open the tool picker and confirm Sprites is listed.
Agent modeCopilot Chat → mode dropdown
Run the first prompt
Ask GitHub Copilot this. It routes to a Sprites door, which reads your AI visibility (AEO) account and answers — no account to name, no confirmation to give first.
- With Sprites, who gets cited when someone asks ChatGPT for the best AI ads platform?
- Ask Sprites to check our AI visibility against our three named competitors.
- Use Sprites to write a comparison page for "us vs [competitor]" and draft it on the site.
- Have Sprites generate an llms.txt from what we actually publish.
- With Sprites, set up a weekly check on our top 20 buying prompts.
Open the Copilot Chat tool picker in agent mode; Sprites appears with its tools, each one toggleable.
What GitHub Copilot can do with AI visibility (AEO)
The same doors, whichever client you are in. Marketing data inside the editor where the tracking code lives, so a conversion event can be checked against what GA4 actually recorded before the pull request is opened.
Find out whether you exist
The prompts your buyers type, run against the answer engines, with who gets named and who does not.
See who is taking the citation
The competitor being cited, and the page the engine is reading to do it.
Write the page that wins it back
Answer pages, FAQ pages and comparison pages, structured the way answer engines actually lift from.
Ship an llms.txt that is not a stub
A real index of what you publish, generated from the site rather than hand-listed and forgotten.
Track it over time
Visibility per prompt per engine, so a change is attributable to the page that caused it.
Get told when it slips
A scheduled check that messages you when a citation you had is gone.
How approvals work here
GitHub Copilot renders tool results as text, so a AEO change comes back written out rather than as a card. Nothing is applied until you approve it, and the approval waits for you in Sprites — open it there and the same run continues.
What it reads
- Answer-engine responses for the prompts you care about
- Which brands and pages get cited, and how often
- Your own site structure and existing answer coverage
- Competitor pages the engines are reading
What it can change
- Answer pages, FAQ pages, comparison and "vs" pages
- llms.txt and entity pages
- All drafted onto your site and published only on approval
When it does not work in GitHub Copilot
Three things go wrong in this client specifically, and each has a one-line fix.
Sprites is configured but Copilot never uses it.
Chat is not in agent mode. Ask mode does not call MCP tools at all.
The config is ignored.
The top-level key is servers. mcpServers is the shape other clients use and VS Code does not read it.
Teammates do not see the connector.
It was added Globally rather than to the Workspace. Move it to .vscode/mcp.json and commit that file; each person still signs in as themselves.
AI visibility (AEO) and GitHub Copilot: questions
Which URL do I paste into GitHub Copilot?
https://mcp.sprites.ai/mcp. There is one endpoint and every client uses it — every OAuth grant is bound to exactly that address, so a variant of it will not be honoured.
Can GitHub Copilot change my AI visibility (AEO) account without asking?
GitHub Copilot renders tool results as text, so a AEO change comes back written out rather than as a card. Nothing is applied until you approve it, and the approval waits for you in Sprites — open it there and the same run continues.
Do I need a AI visibility (AEO) API key or developer token?
No. AI visibility (AEO) is connected once inside Sprites through Your site, plus AI answer-engine tracking, and the connector acts on that connection. GitHub Copilot never sees a credential for it.
Why GitHub Copilot for AI visibility (AEO) specifically?
Marketing data inside the editor where the tracking code lives, so a conversion event can be checked against what GA4 actually recorded before the pull request is opened.
What is AEO?
Answer engine optimization: getting cited in the answers ChatGPT, Perplexity, Claude, Gemini and Google AI Overviews give, rather than ranking in a list of ten blue links. The unit of success is a citation, not a position.
How does it know whether we are cited?
It runs your prompts against the engines and reads the answers, recording which brands and sources are named. It is a measurement, not an estimate.
Keep going
The same GitHub Copilot connector reaches every other channel — nothing else to add.
AI visibility (AEO), from GitHub Copilot
Paste one URL, sign in once, and the next AEO question you ask GitHub Copilot gets answered from the live account.