0–100 scores for ~4,100 US stocks: score a ticker, screen by score and sector, list top scorers.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional. 'Bearer ss_…' personal API key from app.stocksscores.com/developers: 500 calls a day instead of 10, plus alert and watchlist tools.
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.
The 0-100 composite for a symbol with its technical, fundamental and news pillars, the per-timeframe technical scores, and the current quote. Computed live and cached for two hours — the same numbers the analysis page draws.
Ticker, e.g. AAPL
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 stocksscores https://api.stocksscores.com/mcp
Headers
Authorization (optional, not in the config above): Optional. 'Bearer ss_…' personal API key from app.stocksscores.com/developers: 500 calls a day instead of 10, plus alert and watchlist tools.The 0-100 composite for a symbol with its technical, fundamental and news pillars, the per-timeframe technical scores, and the current quote. Computed live and cached for two hours — the same numbers the analysis page draws.
| Argument | Type | Description |
|---|---|---|
| symbol* | string | Ticker, e.g. AAPL |
{
"type": "object",
"required": [
"symbol"
],
"properties": {
"symbol": {
"type": "string",
"description": "Ticker, e.g. AAPL"
}
},
"additionalProperties": false
}Filter last night’s scores across every scoreable US-listed company by score band and sector. Returns compact rows, highest score first. The feed excludes symbols whose fundamental score is missing or built on under 40% of the fundamental weight — closed-end funds, preferred lines and pre-merger shells.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Rows to return (default 25, max 200) |
| sector | string | Exact sector name, e.g. Technology |
| maxScore | number | Only symbols scoring at or below this (0-100) |
| minScore | number | Only symbols scoring at or above this (0-100) |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Rows to return (default 25, max 200)"
},
"sector": {
"type": "string",
"description": "Exact sector name, e.g. Technology"
},
"maxScore": {
"type": "number",
"description": "Only symbols scoring at or below this (0-100)"
},
"minScore": {
"type": "number",
"description": "Only symbols scoring at or above this (0-100)"
}
},
"additionalProperties": false
}The best-scoring symbols in the universe right now, highest first. Ranks only investable names — excludes symbols under $5, under $1B market cap, or with a risk grade above 7. Use screen_stocks to search without that ranking cut.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Rows to return (default 10, max 200) |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Rows to return (default 10, max 200)"
}
},
"additionalProperties": false
}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 14, 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.