standardcompute-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@standardcompute-mcpHow is the Standard Compute endpoint doing?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
standardcompute-mcp
An MCP server for Standard Compute — check the endpoint, list your models, and read current plan pricing from inside any MCP client.
Tools
Tool | What it does | Needs API key |
| Reachability + round-trip latency for the API endpoint | no |
| Current plans/pricing, fetched live from standardcompute.com/llms.txt | no |
| Model ids your key can access ( | yes |
| One tiny end-to-end completion to verify your key works | yes |
All tools are read-only apart from chat_probe, which sends a single ~20-token completion.
Related MCP server: OpenRouter MCP Server
Setup
git clone https://github.com/henrikdukefoss/standardcompute-mcp
cd standardcompute-mcp && npm installClaude Code:
claude mcp add standardcompute -e STANDARDCOMPUTE_API_KEY=your-key -- node /path/to/standardcompute-mcp/src/index.jsClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"standardcompute": {
"command": "node",
"args": ["/path/to/standardcompute-mcp/src/index.js"],
"env": { "STANDARDCOMPUTE_API_KEY": "your-key" }
}
}
}opencode (opencode.json):
{
"mcp": {
"standardcompute": {
"type": "local",
"command": ["node", "/path/to/standardcompute-mcp/src/index.js"],
"environment": { "STANDARDCOMPUTE_API_KEY": "your-key" }
}
}
}Using Magpie? One click adds Standard Compute as a provider (you paste your key in Magpie). Guide: https://standardcompute.com/integrations/magpie
Related guides
On standardcompute.com:
Getting started: create a key and make the first request.
Claude Code setup and OpenCode setup: using the gateway as the model provider in those clients, not only as an MCP server.
Models: the public catalog behind
list_models.Pricing: the plans that
plan_pricingreports.
Environment
STANDARDCOMPUTE_API_KEY— from your dashboard; optional forendpoint_healthandplan_pricingSTANDARDCOMPUTE_BASE_URL— defaults tohttps://api.stdcmpt.com/v1
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Check an MCP endpoint resolves: liveness, live tool list, schema drift. Free.
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Related MCP Servers
AlicenseAqualityBmaintenanceLets MCP clients reach the Lobstack Gateway with a single API key to preview routing and costs without spending anything, run chat completions across every major model, browse the model catalogue, and pull spend reports — with a receipt attached to every call showing which model served it, the token counts, and the cost.417 npmMIT- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to browse and compare model catalogs, pick models by budget or context window, and run completions metered to the caller's own API key.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to browse a live catalog of 100+ models with pricing, rankings and measured uptime, check credits and spend, and send chat completions through an OAuth-authenticated, per-connection key capped by a spend limit. Read tools are free, and paid calls are priced and approved before any credit is used.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to check ChatGPT connection status, list live models, and run prompts using a ChatGPT Plus/Pro plan via OpenAI's official OAuth and Responses API.1Apache 2.0