INDIVIDUAL MCP TOOL
list_instruments
List The Grid's inference instruments: the standardized quality tiers you pass in the `model` field of a Consumption API request.
LIVE ENDPOINT
https://thegrid.ai/mcp
Connect to this endpoint to inspect the live schema for list_instruments and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.thegrid]
url = "https://thegrid.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"thegrid": {
"type": "http",
"url": "https://thegrid.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: thegrid
Remote MCP URL: https://thegrid.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"thegrid": {
"url": "https://thegrid.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"thegrid": {
"type": "http",
"url": "https://thegrid.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "thegrid",
"transport": "streamable-http",
"url": "https://thegrid.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
get_instrument— Full detail for a single instrument: description, current spot price, savings versus list price, context and output limits, recently served models, model distribution, and typical use cases.ask_docs— Ask a natural-language question about The Grid and get an answer with excerpts from the documentation.get_api_overview— Base URLs, authentication schemes, OAuth 2.0 scopes, and the four-step programmatic onboarding path an agent follows to obtain its own consumption API key and start running inference.