Web search, page reading and FLOP miner reliability for agents, priced per call in FLOP.
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 back alerts and whether they have fired.
filter to one miner; default all
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http scout https://flopscout.com/mcp
Read back alerts and whether they have fired.
| Argument | Type | Description |
|---|---|---|
| address | string | filter to one miner; default all |
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "filter to one miner; default all"
}
}
}Subscribe to a settle-rate drop for one miner or all of them ("*"). channel "site" delivers nothing on its own: poll flop_alert_check.
| Argument | Type | Description |
|---|---|---|
| handle | string | Telegram chat id or @username; empty for site |
| address | string | SS58 address, or "*" for every miner |
| channel | string | |
| threshold* | number |
{
"type": "object",
"required": [
"threshold"
],
"properties": {
"handle": {
"type": "string",
"description": "Telegram chat id or @username; empty for site"
},
"address": {
"type": "string",
"description": "SS58 address, or \"*\" for every miner"
},
"channel": {
"enum": [
"site",
"telegram"
],
"type": "string"
},
"threshold": {
"type": "number",
"maximum": 1,
"minimum": 0
}
}
}Every live FLOP model priced as a whole request by the gateway's own estimator: FLOP cost, token split, GFLOPs, latency blocks. Needs no key and spends nothing.
| Argument | Type | Description |
|---|---|---|
| max_tokens | integer |
{
"type": "object",
"properties": {
"max_tokens": {
"type": "integer",
"maximum": 800,
"minimum": 32
}
}
}One miner's settlement history from Scout's own 15-minute snapshots, up to 30 days. A short span means a short history, not a stable rate.
| Argument | Type | Description |
|---|---|---|
| points | integer | |
| window | integer | seconds, default 604800 (7 days) |
| address* | string | SS58 miner address |
{
"type": "object",
"required": [
"address"
],
"properties": {
"points": {
"type": "integer",
"maximum": 500,
"minimum": 2
},
"window": {
"type": "integer",
"description": "seconds, default 604800 (7 days)"
},
"address": {
"type": "string",
"description": "SS58 miner address"
}
}
}FLOP inference miners ranked by settlement rate on chain plus local success and latency.
No arguments.
{
"type": "object",
"properties": {}
}Search the chosen sources and return a cited answer with an itemised price. FLOP answers need a FLOP gateway key in keys.flop; keys.openrouter works for OpenRouter models.
| Argument | Type | Description |
|---|---|---|
| n | integer | results per source |
| q* | string | |
| keys | object | Your own provider keys (flop, openrouter, exa, ...). Never stored or logged. |
| model | string | |
| sources | array | Source ids from scout_catalog. Use ["auto"] to let Scout pick free sources only. |
| max_tokens | integer |
{
"type": "object",
"required": [
"q"
],
"properties": {
"n": {
"type": "integer",
"maximum": 8,
"minimum": 1,
"description": "results per source"
},
"q": {
"type": "string",
"maxLength": 500,
"minLength": 2
},
"keys": {
"type": "object",
"description": "Your own provider keys (flop, openrouter, exa, ...). Never stored or logged.",
"additionalProperties": {
"type": "string"
}
},
"model": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "string"
},
"description": "Source ids from scout_catalog. Use [\"auto\"] to let Scout pick free sources only."
},
"max_tokens": {
"type": "integer",
"maximum": 800,
"minimum": 32
}
}
}List the available sources, presets and models.
No arguments.
{
"type": "object",
"properties": {}
}The full price list in FLOP, the metering mode, and which services are available.
No arguments.
{
"type": "object",
"properties": {}
}Price a request before running it. Spends nothing. With q and model it also returns the FLOP gateway's estimate of the miner's cost as a floor (no sources) and a typical (three sources) figure. Scout's fee and the miner's cost are reported separately.
| Argument | Type | Description |
|---|---|---|
| q | string | The question, to size the inference estimate. |
| model | string | e.g. flop:qwen/qwen2.5-0.5b-instruct |
| sources | array | Source ids from scout_catalog. Use ["auto"] to let Scout pick free sources only. |
| max_tokens | integer |
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "The question, to size the inference estimate."
},
"model": {
"type": "string",
"description": "e.g. flop:qwen/qwen2.5-0.5b-instruct"
},
"sources": {
"type": "array",
"items": {
"type": "string"
},
"description": "Source ids from scout_catalog. Use [\"auto\"] to let Scout pick free sources only."
},
"max_tokens": {
"type": "integer",
"maximum": 800,
"minimum": 32
}
}
}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 15, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.