Bring Georgia's public data straight into Claude, ChatGPT, and Gemini.
A connector lets your AI assistant look up current Georgia data pulled from official sources. Connect it once, ask questions in the tools you already use, and get answers grounded in official data sources.
What it is
A connector, sometimes called an MCP server (Model Context Protocol), is a small bridge between your AI assistant and a source of real information. When you ask about Georgia data your AI assistant (Claude Desktop or ChatGPT) pulls answers automatically from our standardized datasets. Since our datasets come from official sources, you know you are getting accurate and timely responses.
How to connect it
You’ll need an AI assistant on a plan that supports custom connectors (these are usually paid plans), plus the Georgia Civic Data connector address:
https://mcp.georgiacivicdata.org/mcp/There’s no sign-in or password to set up. In every app, the step is simply to paste in that address. (Exact menu names can shift as these apps update.)
Works on the Claude web app, desktop, and phone.
Add it once and it syncs to every Claude app you use, on any device:
- Open Settings → Connectors and click Customize.
- In the Customize window, click the +(Add connector) next to “Connectors,” then choose Add custom connector.
- Fill in a Name(any descriptive name like “Georgia Civic Data” works) and paste the address above into Remote MCP server URL.
- Click Add. You can ignore any “advanced” or OAuth fields.
- To use it in a chat, click the +(or “Search and tools”) and turn it on.
Custom connectors require a Claude Pro or Maxplan. On an organization’s Team or Enterprise plan, an owner adds it once under Organization settings and staff connect to it.
Add it from the ChatGPT website (not the app).
You have to add the connector from ChatGPT on the web; the phone and desktop apps don’t offer this yet.
- Open Settings → Apps, and next to Advanced settings click Create app.
- In the New App dialog, enter a Name(any descriptive name like “Georgia Civic Data” works).
- Leave Connection set to Server URL and paste the address above.
- Set Authentication to No Auth.
- Check I understand and want to continue, click Create, then click Connect.
Menu names can shift as ChatGPT updates; for the latest steps and which plans qualify, see OpenAI’s Developer Mode guide.
Today, Gemini support is through the Gemini CLI.
Google’s consumer Gemini app doesn’t yet let you add custom connectors. If you (or your organization’s IT) use the Gemini CLI (a tool that runs in a terminal), add the connector to ~/.gemini/settings.json:
{
"mcpServers": {
"georgia-civic-data": {
"httpUrl": "https://mcp.georgiacivicdata.org/mcp/"
}
}
}Restart the Gemini CLI and run /mcp to confirm it connected.
Things you can ask once it's connected
- “Show graduation rates by district in metro Atlanta over the last five years.”
- “How have ACT scores changed in this district over the past decade?”
- “Which schools in Fulton County have the lowest ELA proficiency rates?”
- “Compare enrollment by grade level across two districts.”
- “What datasets do you have, and what does each one cover?”
Why it beats asking ChatGPT or Claude directly
- Straight from the source. It reads our standardized datasets that come from official sources, not whatever happened to be in the model's training data or whatever appeared in a search.
- No made-up numbers. It returns the data that exists, or tells you when a value is suppressed or unavailable, instead of inventing figures.
- Cross-dataset linking built in. Shared keys let it join datasets that would otherwise take custom data engineering.
- Always current. Newly published datasets appear automatically, with no change on your end.
Good to know
- It only looks things up. The connector reads public data. It does not change anything and does not store, or look at, your conversations.
- No sign-in required. The data is public, so the connector itself needs no account or key. A paid AI plan may still be required to add custom connectors.
- Not a government service. This connects to Georgia Civic Data, an independent, non-partisan project. It is not affiliated with the State of Georgia or any state agency.
The tools it exposes
Under the hood the connector offers a small set of tools your assistant calls for you. You do not need to learn them, but here is what it can do:
- Find datasets. List and search the full catalog of topics and dimensions.
- Inspect a dataset. Read its columns, filter keys, and the valid values for each filter.
- Query and aggregate. Pull filtered rows, or get server-side averages, sums, and counts grouped by year, place, or category.
- Resolve labels. Look up district, school, and demographic names from the shared dimension tables.
- Browse a dimension. Page through the full list of districts, schools, or demographic labels, plus the shared table's schema and cross-dataset link keys.
- Read the contract. Fetch a dataset's full machine-readable schema and documentation.
- Link across datasets. Discover and run guarded, read-only cross-dataset joins.