datacenterindex
AI infrastructure data for agents: data center campuses in the US and abroad, the power projects built for them, and the public companies involved.
What it can do
- Search Projects: Search tracked data center projects. Filter by free-text query (name, developer, tenant, city), US state code, status, developer, or minimum MW. Returns up to 50 rows sorted by capaci
- Get Project: One tracked project by slug (the last path segment of a datacenterindex.ai/projects/... URL), with its linked public companies.
- List Markets: Every US state market with tracked projects: counts by status, pipeline MW, grid operator, page URL.
What data it sees
Do you need an account
No: the server works without sign-in
AI infrastructure data for agents: data center campuses in the US and abroad, the power projects built for them, and the public companies involved. Each campus has status, developer, capacity and cost. Every capacity figure says whether a named source states it or it's an estimate, and every result links its source. 8 read-only tools, free to try, free key for 1,000 calls a day.
How to connect
How to connect datacenterindex to Claude
The server address to paste into Claude settings:
https://datacenterindex--tkirwan123.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect datacenterindex to ChatGPT
The server address to paste into ChatGPT settings:
https://datacenterindex--tkirwan123.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect datacenterindex to Cursor
The server address to paste into Cursor settings:
https://datacenterindex--tkirwan123.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (8)
Raw names from tools/list. Only developers need these.
| search_projects | Search tracked data center projects. Filter by free-text query (name, developer, tenant, city), US state code, status, developer, or minimum MW. Returns up to 50 rows sorted by capacity. |
| get_project | One tracked project by slug (the last path segment of a datacenterindex.ai/projects/... URL), with its linked public companies. |
| list_markets | Every US state market with tracked projects: counts by status, pipeline MW, grid operator, page URL. |
| get_market | One US state market: summary description, counts, the tracked projects, and the public companies exposed to it. |
| list_companies | Public companies in the tracked supply-chain universe with sector, data-center revenue exposure and project count. |
| get_company | One public company by ticker: description, data-center exposure, market cap, and the tracked projects it is linked to. |
| get_movers | Biggest day and week stock moves across the tracked universe (latest close). |
| recent_changes | What changed in the tracker recently: new projects, status changes, capacity revisions. The single source for "what is new". |