mcpField
A
aidc-mcp-server

aidc-mcp-server

Local
aidc-ai.ioCloud & Infra

About aidc-mcp-server

AIDC MCP for OPR/BOD sizing, validation, and rackPlan layout from the shared 3D graph

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"aidc2026ai-melon-aidc": {
"command": "npx",
"args": [
"-y",
"aidc-mcp-server"
],
"env": {
"AIDC_API_KEY": "<AIDC_API_KEY>"
}
}
}
}
Run commandnpx -y aidc-mcp-server
Environment variables to set
AIDC_API_KEYSecretRegistered AIDC integration key. Obtain access through https://aidc-ai.io/contact.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmaidc-mcp-server0.2.4

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
gpuGenenumYesNVIDIA GPU generation: hopper, blackwell, or rubin.hopper | blackwell | rubin
regionenumYesMetropolitan or regional site class.metropolitan | regional
optionsobjectNoOptional redundancy, cooling-mode, and PUE overrides.
options.pueTargetnumberNo
options.redundancyenumNon | n_plus_1 | 2n
options.coolingModeenumNoair | hybrid | liquid
parcelsarrayNoOptional bounded GeoJSON parcel features.
itLoadMwnumberYesIT load in megawatts. 0 < x <= 1000.
hallCountintegerNoOptional requested data-hall count.
siteAreaSqmnumberYesTotal site area in square meters.
customInputsobjectNoOptional project-specific design inputs.
rackDensityKwnumberYesRequested per-rack power in kW. 0 < x <= 500.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.