Timefire's public record of AI stock forecasts: graded books, track record and proof.
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.
Get the evidence behind one prediction in a resolved book: pick context, news, notes.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http record https://api.timefire.ai/mcp/
Get the evidence behind one prediction in a resolved book: pick context, news, notes.
| Argument | Type | Description |
|---|---|---|
| ticker* | string | |
| trading_date* | string |
{
"type": "object",
"title": "explain_resolved_predictionArguments",
"required": [
"trading_date",
"ticker"
],
"properties": {
"ticker": {
"type": "string",
"title": "Ticker"
},
"trading_date": {
"type": "string",
"title": "Trading Date"
}
}
}Get a resolved book's portfolio: market-cap-weighted vs SPY ("cap", the default, the portfolio the ledger's verdict grades) or equal-weighted vs RSP ("equal"), with each long pick's weight and graded return, the book return, the benchmark return and its evidence, alpha and verdict. Equal weights always pair with RSP and cap weights with SPY. Per prediction, books serve the two as equal_weight and market_cap_weight; never read a pick's cap_weight as either without checking inference_metadata.weighting.
| Argument | Type | Description |
|---|---|---|
| weighting | string | |
| trading_date* | string |
{
"type": "object",
"title": "get_book_portfolioArguments",
"required": [
"trading_date"
],
"properties": {
"weighting": {
"type": "string",
"title": "Weighting",
"default": "cap"
},
"trading_date": {
"type": "string",
"title": "Trading Date"
}
}
}Get calibration computed only from fully resolved books.
No arguments.
{
"type": "object",
"title": "get_calibrationArguments",
"properties": {}
}Get a full batch only after its long-pick book is fully resolved.
| Argument | Type | Description |
|---|---|---|
| trading_date* | string |
{
"type": "object",
"title": "get_resolved_batchArguments",
"required": [
"trading_date"
],
"properties": {
"trading_date": {
"type": "string",
"title": "Trading Date"
}
}
}Get the paper portfolio's NAV series, market-cap-weighted vs SPY ("cap", the default) or equal-weighted vs RSP ("equal"), with both benchmarks on every row: one row per resolved trading day, through the newest book date through which every book is revealed: a later value holds positions from books still sealed.
| Argument | Type | Description |
|---|---|---|
| to_date | any | |
| from_date | any | |
| weighting | string |
{
"type": "object",
"title": "get_simulation_navArguments",
"properties": {
"to_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "To Date",
"default": null
},
"from_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "From Date",
"default": null
},
"weighting": {
"type": "string",
"title": "Weighting",
"default": "cap"
}
}
}Get the paper portfolio's closed trades from resolved books, newest first, market-cap-weighted ("cap", the default) or equal-weighted ("equal"): the two trade at the same prices and differ in weight, and so in size and P&L. Open positions never appear.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| to_date | any | |
| from_date | any | |
| weighting | string |
{
"type": "object",
"title": "get_simulation_tradesArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 500
},
"to_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "To Date",
"default": null
},
"from_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "From Date",
"default": null
},
"weighting": {
"type": "string",
"title": "Weighting",
"default": "cap"
}
}
}Get one ticker's observations from resolved books only.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| ticker* | string |
{
"type": "object",
"title": "get_stock_resolved_historyArguments",
"required": [
"ticker"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 120
},
"ticker": {
"type": "string",
"title": "Ticker"
}
}
}Get aggregates computed only from fully resolved books: prediction counts, returns and hit rates, and how many books beat, matched (flat) or trailed SPY, each book's verdict graded on its cap-weighted long picks. The hit rates count the books graded under the published rule, from published_rule_from on; the 69 backtest books before it follow a rule of their own and are reported apart in the backtest_ fields, verdicts included.
No arguments.
{
"type": "object",
"title": "get_track_record_statsArguments",
"properties": {}
}Get the versioned scoring rules and latest resolved-book universe.
No arguments.
{
"type": "object",
"title": "get_universe_and_scoring_specArguments",
"properties": {}
}List resolved batch summaries, newest first.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| to_date | any | |
| from_date | any |
{
"type": "object",
"title": "list_resolved_batchesArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 60
},
"to_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "To Date",
"default": null
},
"from_date": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "From Date",
"default": null
}
}
}Find the developer guides and site pages that match a few words. Each hit carries the page title, its canonical URL and a short excerpt.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string |
{
"type": "object",
"title": "search_docsArguments",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 5
},
"query": {
"type": "string",
"title": "Query"
}
}
}Get the complete public verification record for a resolved batch.
| Argument | Type | Description |
|---|---|---|
| trading_date* | string |
{
"type": "object",
"title": "verify_batchArguments",
"required": [
"trading_date"
],
"properties": {
"trading_date": {
"type": "string",
"title": "Trading Date"
}
}
}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 7, 2026.