Free report: how many of your LLM's classification calls a small CPU model can answer alone.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Read-only, never pays: for a certified (fit) report, returns the $99 offer to keep the model, the question to ask the user word for word, a card checkout link for the user, and the USDC (x402) payment details when the server offers them. If the job is not buyable, returns the reason.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http nogpu https://nogpu.dev/mcp
https://github.com/doronp/nogpu-mcp/releases/download/v0.2.2/nogpu-mcp-0.2.2.mcpbRead-only, never pays: for a certified (fit) report, returns the $99 offer to keep the model, the question to ask the user word for word, a card checkout link for the user, and the USDC (x402) payment details when the server offers them. If the job is not buyable, returns the reason.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| claim_token* | string |
{
"type": "object",
"title": "nogpu_buyArguments",
"required": [
"job_id",
"claim_token"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
},
"claim_token": {
"type": "string",
"title": "Claim Token"
}
}
}Delete an uploaded job's data now (otherwise deleted within 24h, or 24h after payment if you bought the model).
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| claim_token* | string |
{
"type": "object",
"title": "nogpu_deleteArguments",
"required": [
"job_id",
"claim_token"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
},
"claim_token": {
"type": "string",
"title": "Claim Token"
}
}
}Free report: send an LLM's past decisions, 160-10,000 rows with at least 2 labels, either as `rows` ([{"text": ..., "label": ...}]) or as `jsonl` (the same rows as JSONL text; a JSON array or a CSV with a header row also works), at most 20 MB. NoGPU trains a small CPU model on them and measures what share of the decisions it answers alone, how often those answers match the LLM (with a 95% lower bound) on held-out rows, and its latency. Waits up to 40 seconds; if the report is not ready by then, call nogpu_status with the returned job_id and claim_token. claim_token and report_url (the token is after its #) open the job: treat both as secrets. Free reports through this endpoint come from one shared daily pool. Data is deleted within 24h. `source` says where the rows came from: agent (default), the app's stored history, rows logged by a collect snippet, or a given file.
| Argument | Type | Description |
|---|---|---|
| rows | any | |
| jsonl | any | |
| source | string |
{
"type": "object",
"$defs": {
"Row": {
"type": "object",
"title": "Row",
"required": [
"text",
"label"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
},
"label": {
"type": "string",
"title": "Label"
}
}
}
},
"title": "nogpu_reportArguments",
"properties": {
"rows": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/Row"
}
},
{
"type": "null"
}
],
"title": "Rows",
"default": null
},
"jsonl": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Jsonl",
"default": null
},
"source": {
"enum": [
"agent",
"history",
"logging",
"file"
],
"type": "string",
"title": "Source",
"default": "agent"
}
}
}A job's status, and its report once ready (same fields as nogpu_report). Also shows download_url after payment: GET it with header X-Claim-Token. claim_token and report_url are secrets.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| claim_token* | string |
{
"type": "object",
"title": "nogpu_statusArguments",
"required": [
"job_id",
"claim_token"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
},
"claim_token": {
"type": "string",
"title": "Claim Token"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.