GPUQuant MCP server
Commit Sep 13, 2026Allows an AI agent to search AI infrastructure records, inspect facility facts, and explore sourced company relationships.
Also known as gpuquant/mcp, mcp
- Stars
- 0
- Tools
- 3
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Sep 13, 2026
- License
- MIT
What is GPUQuant MCP?
GPUQuant allows an AI agent to search AI infrastructure records, inspect facility facts, and explore sourced company relationships. It exposes 3 tools, such as search_infrastructure, get_facility, get_company.
Summary generated from the project's README
About GPUQuant MCP server
GPUQuant AI Infrastructure provides an MCP server that connects AI agents to sourced records regarding AI hardware facilities and corporate connections. Developers can integrate this service into MCP-compatible applications using a streamable HTTP connection via the provided URL. This public service does not require an API key for access.
The server offers three primary tools for data retrieval. Users can utilize search_infrastructure to locate records by name or location with pagination, get_facility to examine public facts and verification context, and get_company to investigate documented company relationships. Every result includes canonical URLs that link back to the original GPUQuant records and their supporting sources.
This tool is designed for research and context rather than financial execution. It distinguishes itself by providing transparency regarding unknown values and verification dates. It does not provide access to licensed feeds, trading accounts, imagery, or building geometry. The service focuses on infrastructure records and supply-chain relationships to help agents identify stale or unknown facts.
What you can do with it
- 1Locate regional infrastructureAsk an agent to find specific AI infrastructure records located in a particular city and display their sources.
- 2Verify facility detailsRequest information about a facility's operator and the date its status was last verified.
- 3Analyze corporate relationshipsInvestigate which supply-chain connections are officially documented versus those that are merely reported.
- 4Identify data gapsInstruct an agent to find missing or outdated information before it summarizes a company's infrastructure.
Written from the project's README. Every use case is checked against a quote from it.
How to install GPUQuant MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall GPUQuant MCP in Claude Code
$ claude mcp add --transport http mcp https://gpuquant.com/api/mcpInstall GPUQuant MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://gpuquant.com/api/mcp"
}
}
}Install GPUQuant MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://gpuquant.com/api/mcp"
}
}
}Install GPUQuant MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"http","url":"https://gpuquant.com/api/mcp"}'Install GPUQuant MCP in Codex
$ codex mcp add mcp --url https://gpuquant.com/api/mcpInstall GPUQuant MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] url = "https://gpuquant.com/api/mcp"
Install GPUQuant MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp https://gpuquant.com/api/mcpInstall GPUQuant MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"url": "https://gpuquant.com/api/mcp",
"type": "http"
}
}
}GPUQuant MCP tools 3
Detected from the READMEsearch_infrastructureget_facilityget_company
| search_infrastructure | — | |
| get_facility | — | |
| get_company | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegpuquant/mcp is public and reachablegithub.com/gpuquant/mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-13github.com/gpuquant/mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model3 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeEndpoint did not answer initialize: HTTP 530Finding
README
View on GitHubGPUQuant MCP
Connect an AI agent to sourced AI infrastructure records from GPUQuant.
GPUQuant's hosted MCP provides read-only tools for finding infrastructure, inspecting facility facts and checking company relationships. Results link to GPUQuant records and their supporting sources, retaining verification dates and unknown values.
Connection URL: https://gpuquant.com/api/mcp
Transport: Streamable HTTP. No API key is required for this public infrastructure service.
This repository contains connection instructions, the registry manifest and a reproducible HTTP smoke test. The hosted service runs on GPUQuant; cloning this repository does not copy or self-host GPUQuant's database.
Connect
In an MCP-compatible application's remote-server settings, add the connection URL above. Use the application's own remote MCP support; configuration format varies by client.
For clients using the VS Code mcp.json format:
{
"servers": {
"gpuquant": {
"type": "http",
"url": "https://gpuquant.com/api/mcp"
}
}
}
See the GPUQuant connection guide and your client's current MCP documentation. The endpoint supports the current MCP protocol and legacy clients using the 2025 initialization handshake.
Tools
| Tool | Purpose |
|---|---|
search_infrastructure |
Find infrastructure records by name or location with bounded pagination |
get_facility |
Read a facility's public facts, sources and verification context |
get_company |
Read company facts and sourced relationships |
Use tools/list to obtain the exact current input schemas. Results include canonical GPUQuant URLs so readers can open the underlying record and report a correction.
Example questions
- “Find infrastructure records mentioning Copenhagen and show their sources.”
- “What does GPUQuant know about this facility's operator and status, and when was it verified?”
- “Which supply-chain relationships are documented for this company, and which are only reported?”
- “Identify unknown or stale facts before summarizing this company's infrastructure.”
Coverage and interpretation
The first release focuses on infrastructure records and company relationships. It does not expose licensed Ornn or Silicon Data feeds, trading accounts, orders, imagery, building geometry or raw source excerpts. Dates describe the underlying records or sources; a retrieval timestamp is not a fresh verification of a fact.
Announced capacity, construction and operating capacity are different claims. Missing values remain unknown. Supporting sources may describe different dates or scopes; inspect them before relying on a comparison. The MCP supplies research context and does not place trades or provide investment recommendations.
Check the connection
Requires Node.js 20 or newer. No packages or credentials are needed:
node scripts/smoke.mjs
The script checks initialization, tool discovery, all three tools against real records, and current-protocol discovery. To test a development endpoint:
node scripts/smoke.mjs http://localhost:3000/api/mcp
Corrections and connection issues
- Report an incorrect infrastructure record.
- Report an MCP connection issue.
- Contact GPUQuant for data access and partnerships.
The MIT license applies to this repository's original documentation and example code. Data and linked sources retain their own terms. Methodology · Map · Community
GPUQuant MCP questions
How do I add GPUQuant MCP to Claude Code?
Run claude mcp add --transport http mcp https://gpuquant.com/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add GPUQuant MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does GPUQuant MCP provide?
It exposes 3 tools, including search_infrastructure, get_facility, get_company.
Do I need an API key to use this service?
No, this is a public infrastructure service that does not require an API key.
Can I self-host the GPUQuant database by cloning this repository?
No, cloning the repository only provides connection instructions and tests; the service runs on GPUQuant's hosted infrastructure.
Does this server provide investment recommendations?
No, the MCP provides research context only and does not provide investment recommendations or place trades.