此 MCP 可以做什么
Runs and compares historical trading strategy backtests, computes performance statistics, retrieves market and macroeconomic data, and exports results.
功能
工具
20
工具
compare_backtests
Run several strategies on the same data and compare side by side.
One quota-counted call, but compute scales with the number of
strategies. If the wall-clock compute budget is exceeded, the call
fails with a tool error (504) instead of returning partial results â
narrow the request (fewer strategies, shorter date range, coarser
frequency) and retry.
Args:
data_source: Shared data source (same shape as run_backtest).
strategies: List of {"label": str, "strategy": {...},
"execution": {...}?} entries. Labels need not be unique or
id-safe â they are echoed back verbatim in the result.
include_benchmark: Add a buy-and-hold benchmark to the comparison.
response_detail: Shaping level applied to each strategy's result.
trades_limit: Max trades per strategy when detail is 'full'.
Returns:
{"strategies": [{"label", "result"}, ...], "equity_curves": {...},
"alignment"?}, each result shaped at the requested detail. When a
benchmark is included, non-benchmark entries also carry
"relative" (beta, alpha, information ratio, etc.). A 400/422
rejection returns {"accepted": false, "error": ...};
capacity/timeout/permission failures raise a tool error.
输入模式
{'type': 'object', 'title': 'compare_backtestsArguments', 'required': ['data_source', 'strategies'], 'properties': {'strategies': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Strategies'}, 'data_source': {'type': 'object', 'title': 'Data Source', 'additionalProperties': True}, 'trades_limit': {'type': 'integer', 'title': 'Trades Limit', 'default': 50}, 'response_detail': {'enum': ['summary', 'stats', 'full'], 'type': 'string', 'title': 'Response Detail', 'default': 'summary'}, 'include_benchmark': {'type': 'boolean', 'title': 'Include Benchmark', 'default': False}}}
输出模式
{'type': 'object', 'title': 'compare_backtestsDictOutput', 'additionalProperties': True}
compute_stats
Compute the engine's performance metrics from a returns series.
Use when the returns came from somewhere
other than run_backtest (an external system, a portfolio) â backtest
results already include these statistics.
Args:
returns: Per-bar log returns as {"dates": [...], "values": [...]}
parallel arrays (ISO-8601 dates).
trading_days_per_year: Required annualization factor â 252 for a
daily equities calendar, 365 for 24/7 crypto. Must match the bar
calendar of the returns series; a wrong value silently
mis-annualizes Sharpe, volatility, and CAGR.
benchmark_returns: Optional benchmark series, same shape â adds
alpha/beta/capture metrics.
trades: Optional trade records (entry_date, exit_date, direction,
return_net, ...) â adds trade-level metrics.
risk_free_rate: Annual risk-free rate as a decimal.
Returns:
{"stats": {...}} â the metric set the API key's plan allows.
See get_catalog('sections') for every metric's id and description.
输入模式
{'type': 'object', 'title': 'compute_statsArguments', 'required': ['returns', 'trading_days_per_year'], 'properties': {'trades': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, {'type': 'null'}], 'title': 'Trades', 'default': None}, 'returns': {'type': 'object', 'title': 'Returns', 'additionalProperties': True}, 'risk_free_rate': {'type': 'number', 'title': 'Risk Free Rate', 'default': 0.0}, 'benchmark_returns': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Benchmark Returns', 'default': None}, 'trading_days_per_year': {'type': 'integer', 'title': 'Trading Days Per Year'}}}
输出模式
{'type': 'object', 'title': 'compute_statsDictOutput', 'additionalProperties': True}
engine_info
Engine version, API contract number, and health.
Free (not quota-counted). Call once at the start of a session
to confirm the engine is reachable and which contract it serves.
输入模式
{'type': 'object', 'title': 'engine_infoArguments', 'properties': {}}
输出模式
{'type': 'object', 'title': 'engine_infoDictOutput', 'additionalProperties': True}
export_backtest
Export a multi-strategy comparison as an Excel workbook.
Quota-counted; needs a key whose plan includes full-metrics export
(a 403 means the configured key's plan does not â do not retry).
Returns the workbook base64-encoded â decode and write it to a
``.xlsx`` file.
Args:
data_source: Shared data source (same shape as run_backtest).
strategies: Same shape as compare_backtests' ``strategies``.
include_benchmark: Add a buy-and-hold benchmark to the export.
Returns:
{"filename", "content_type", "size_bytes", "content_base64"}. A
400/422 rejection returns {"accepted": false, "error": ...};
capacity/timeout/permission failures raise a tool error. If the
encoded workbook would exceed the output size limit, raises a
tool error â narrow the request (shorter date range, fewer
strategies, coarser frequency) and retry.
输入模式
{'type': 'object', 'title': 'export_backtestArguments', 'required': ['data_source', 'strategies'], 'properties': {'strategies': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Strategies'}, 'data_source': {'type': 'object', 'title': 'Data Source', 'additionalProperties': True}, 'include_benchmark': {'type': 'boolean', 'title': 'Include Benchmark', 'default': False}}}
输出模式
{'type': 'object', 'title': 'export_backtestDictOutput', 'additionalProperties': True}
get_catalog
Fetch one engine reference catalog.
Catalogs (cheap, cacheable per session):
- 'operators' â comparison operators for condition expressions
- 'execution-modes' â entry/exit anchors and fill algorithms, with the
validity matrix by market type
- 'stop-types' â stop-loss types, re-entry modes, and their parameters
- 'sizing-methods' â position-sizing methods and their parameters
- 'bar-frequencies' â supported bar frequencies and the signal x
execution validity matrix (which combinations are allowed)
- 'sections' â the full metric catalog: every statistic's stable id,
display label, section, and description
- 'sampling-modes' â Monte-Carlo resampling modes, each with its
status and parameters
Fetch the relevant catalog BEFORE building a strategy or config; build
only from values it lists â never guess parameter names or frequencies.
输入模式
{'type': 'object', 'title': 'get_catalogArguments', 'required': ['catalog'], 'properties': {'catalog': {'enum': ['operators', 'execution-modes', 'stop-types', 'sizing-methods', 'bar-frequencies', 'sections', 'sampling-modes'], 'type': 'string', 'title': 'Catalog'}}}
输出模式
{'type': 'object', 'title': 'get_catalogDictOutput', 'additionalProperties': True}
get_data_range
Available date range and estimated bar count for a symbol/frequency.
Available on paid plans. Call before a server-side fetch so the
requested start/end stay inside what the provider can deliver and the
bar count stays inside the key's per-run limit.
输入模式
{'type': 'object', 'title': 'get_data_rangeArguments', 'required': ['symbol', 'frequency'], 'properties': {'symbol': {'type': 'string', 'title': 'Symbol'}, 'frequency': {'type': 'string', 'title': 'Frequency'}}}
输出模式
{'type': 'object', 'title': 'get_data_rangeDictOutput', 'additionalProperties': True}
get_latest_signal
Evaluate the strategy on the most recent bar only â no P&L, no stats.
Returns the latest signal (-1/0/1), which
condition slots fired, and the bar timestamp. Use for "what would this
strategy do right now" questions; use run_backtest for performance.
输入模式
{'type': 'object', 'title': 'get_latest_signalArguments', 'required': ['data_source', 'strategy'], 'properties': {'strategy': {'type': 'object', 'title': 'Strategy', 'additionalProperties': True}, 'execution': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Execution', 'default': None}, 'data_inputs': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Data Inputs', 'default': None}, 'data_source': {'type': 'object', 'title': 'Data Source', 'additionalProperties': True}}}
输出模式
{'type': 'object', 'title': 'get_latest_signalDictOutput', 'additionalProperties': True}
get_macro_series
Observations for one macroeconomic series over an optional date range.
Free â no special plan. ``series`` is an ``id`` from list_macro_series
(e.g. treasury_10y, cpi, unemployment_rate); arbitrary external ids are
not accepted. ``start``/``end`` are ``YYYY-MM-DD``, inclusive, both
optional (full history when omitted). Returns the value series at its
native reporting frequency, with the series descriptor and an ``as_of``
date. A long history is downsampled by the MCP server to a bounded
number of points (first and last kept), marked with
``downsampled_from_bars`` and ``points_returned`` on the
``observations`` block.
Note: values are the latest revised figures stamped by reference period,
not point-in-time as-first-reported data â do not treat them as the
values that were known at a past date.
输入模式
{'type': 'object', 'title': 'get_macro_seriesArguments', 'required': ['series'], 'properties': {'end': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'End', 'default': None}, 'start': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Start', 'default': None}, 'series': {'type': 'string', 'title': 'Series'}}}
输出模式
{'type': 'object', 'title': 'get_macro_seriesDictOutput', 'additionalProperties': True}
get_me
The configured API key's permissions, limits, and current usage.
Cheap. Call early in a session â before planning work â to learn what
this key can do instead of discovering limits through failed calls.
Returns:
``scopes``: the permission scopes the key carries. ``limits``:
requests per minute and per day, max concurrent requests, and the
per-run bar cap (null when uncapped). ``usage``: current
consumption against those limits, with reset countdowns in
seconds. ``capabilities``: feature flags such as server-side data
fetch and the full metric set. A small fixed-shape record,
returned as the engine sent it.
输入模式
{'type': 'object', 'title': 'get_meArguments', 'properties': {}}
输出模式
{'type': 'object', 'title': 'get_meDictOutput', 'additionalProperties': True}
get_price_history
OHLCV price history for a symbol over a date range.
Requires a paid plan (managed market data). ``start`` is required
(``YYYY-MM-DD``); ``end`` defaults to today. Returns a summary (symbol,
resolved date range, total bar count, price range, gap flags),
market-hours detection, and the OHLCV arrays. A long history is
downsampled by the MCP server to a bounded number of points â first and
last bar always kept, every column thinned on the same dates â with
``downsampled_from_bars`` and ``points_returned`` recorded on the
``ohlcv`` block; the untouched ``summary.total_bars`` still reports the
true bar count. The window is bounded by the plan's per-request bar cap
â call get_data_range first to size a request.
输入模式
{'type': 'object', 'title': 'get_price_historyArguments', 'required': ['symbol', 'start'], 'properties': {'end': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'End', 'default': None}, 'start': {'type': 'string', 'title': 'Start'}, 'symbol': {'type': 'string', 'title': 'Symbol'}, 'frequency': {'type': 'string', 'title': 'Frequency', 'default': 'daily'}}}
输出模式
{'type': 'object', 'title': 'get_price_historyDictOutput', 'additionalProperties': True}
get_quote
Latest available price for a symbol.
Requires a paid plan (managed market data). Returns the most recent
*available* bar for the given frequency â the end-of-day close for
daily, the last completed bar otherwise â as open/high/low/close/volume
plus an ``as_of`` timestamp for that bar. This is a last-known price,
not a live tick; read ``as_of`` to judge how stale it is.
输入模式
{'type': 'object', 'title': 'get_quoteArguments', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'title': 'Symbol'}, 'frequency': {'type': 'string', 'title': 'Frequency', 'default': 'daily'}}}
输出模式
{'type': 'object', 'title': 'get_quoteDictOutput', 'additionalProperties': True}
get_strategy_schema
JSON Schema for the strategy document (condition_tree + indicators).
Fetch this before composing a strategy by hand; the
validate_strategy tool checks against the same rules.
输入模式
{'type': 'object', 'title': 'get_strategy_schemaArguments', 'properties': {}}
输出模式
{'type': 'object', 'title': 'get_strategy_schemaDictOutput', 'additionalProperties': True}
get_ticker_info
Identity and data coverage for one symbol, in a single call.
Metadata only â no market data, so no paid plan is needed. Returns the
asset's identity (name, asset class, exchange, currency, and whether it
is still active) together with a coverage summary for the given
frequency: the available date range and an estimated bar count. Use it
to confirm a symbol resolves and that the history you need exists before
requesting a quote or a price fetch. For the precise per-frequency range
use get_data_range.
输入模式
{'type': 'object', 'title': 'get_ticker_infoArguments', 'required': ['symbol'], 'properties': {'symbol': {'type': 'string', 'title': 'Symbol'}, 'frequency': {'type': 'string', 'title': 'Frequency', 'default': 'daily'}}}
输出模式
{'type': 'object', 'title': 'get_ticker_infoDictOutput', 'additionalProperties': True}
list_indicators
List indicators, or fetch one indicator's full schema.
Cheap, cacheable per session.
With no arguments: a compact catalog â ``{"indicators": [...],
"count": N}`` â where each entry carries id, name, category, kind,
and value_dtype (no description, to keep the discovery scan small). Use
it to discover what exists. Pass name='rsi' (id or name,
case-insensitive) to get that single indicator's complete entry
including its description and params_schema â do this before adding an
indicator to a strategy so its parameters are exactly right.
Pass compact=False for full entries for everything (large; the MCP
server may cap it and set ``truncated_by_mcp`` â prefer compact or
name=).
Wire optimization: the compact discovery path asks the engine to omit
per-entry descriptions (``descriptions=false``) since they are stripped
locally anyway; the name= and compact=False paths request them. This is
a pure saving â if the engine ignores the param it returns full entries
and the local compact strip still yields a lean result.
输入模式
{'type': 'object', 'title': 'list_indicatorsArguments', 'properties': {'name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Name', 'default': None}, 'compact': {'type': 'boolean', 'title': 'Compact', 'default': True}}}
list_macro_series
List the available macroeconomic series (the catalog).
Free â no special plan. Returns the set of macro series you can fetch
with get_macro_series, each with its stable ``id`` (the value
get_macro_series takes), title, category, native reporting frequency,
and units, plus the list of categories. Optionally filter to one
``category`` (e.g. rates, yield_curve, inflation, employment, recession,
growth). Call this first to find the ``id`` for the series you want.
输入模式
{'type': 'object', 'title': 'list_macro_seriesArguments', 'properties': {'category': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Category', 'default': None}}}
输出模式
{'type': 'object', 'title': 'list_macro_seriesDictOutput', 'additionalProperties': True}
list_templates
List predesigned strategy templates, or fetch one in full.
Cheap, cacheable per session. The engine returns the templates
available to the calling key.
With no arguments: a compact catalog â ``{"templates": [...],
"count": N}`` â where each entry carries id, origin, name, and
description. Use it to discover what exists. Pass name='sma-cross'
(id or name, case-insensitive) to get that single template's complete
entry: its strategy logic (``condition_tree`` + ``indicators``, the
same shape validate_strategy and run_backtest accept) plus parameter
metadata â ``defaults`` (starting parameter values), ``requires``,
and ``locked_params`` (parameters that must keep their template
values). Pass compact=False for complete entries for everything
(large; the MCP server may cap it and set ``truncated_by_mcp`` â
prefer compact or name=).
输入模式
{'type': 'object', 'title': 'list_templatesArguments', 'properties': {'name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Name', 'default': None}, 'compact': {'type': 'boolean', 'title': 'Compact', 'default': True}}}
list_tickers
List available tickers, optionally filtered by asset class.
The full universe is very large, so the MCP server
caps the returned list and marks it ``truncated_by_mcp`` â pass
asset_class to narrow it, or use search_tickers to resolve a specific
asset by name.
输入模式
{'type': 'object', 'title': 'list_tickersArguments', 'properties': {'asset_class': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Asset Class', 'default': None}}}
输出模式
{'type': 'object', 'title': 'list_tickersDictOutput', 'additionalProperties': True}
run_backtest
Run a historical backtest against the engine.
Quota-counted and compute-bound. Validate the
strategy first (validate_strategy is far cheaper). On a 504 compute
timeout, do NOT retry the same request â reduce the date range, use a
coarser frequency, or simplify the strategy. On 429/503, wait for the
advertised Retry-After before retrying.
Args:
data_source: Either inline OHLCV ({"ohlcv": {dates, open, high,
low, close, volume?}} as parallel arrays, ISO-8601 dates) or a
server-side fetch ({"symbol", "start", "end", "frequency"} â
requires a paid plan).
strategy: Strategy document (indicators[] + condition_tree).
Mutually exclusive with signals.
signals: Precomputed signal series ({"dates": [...], "values":
[-1|0|1, ...]}). Mutually exclusive with strategy.
execution: Execution/cost/risk/sizing settings. Use values from
get_catalog('execution-modes'/'stop-types'/'sizing-methods');
omit for engine defaults.
benchmark: Optional benchmark data source (same shape as
data_source) â when given, the result also carries
benchmark-relative metrics (beta, alpha, information ratio,
tracking error, up/down capture) and bar-alignment info.
data_inputs: Optional custom time-series the strategy references
(name -> {dates, values}).
response_detail: 'summary' (default â headline metrics, smallest),
'stats' (every metric), 'full' (plus trades and series
downsampled to a fixed, server-controlled number of points).
include: Optional add-on blocks at any detail level: 'trades',
'equity_curve', 'monthly_returns', 'yearly_returns',
'signal_diagnostics' (which per-bar entry/exit conditions
fired, as capped fire-date lists â {"available": false, ...}
if the run has none, e.g. precomputed signals).
trades_limit: Max trades returned when trades are included.
Returns:
The shaped result at the requested detail (including
``benchmark_relative``/``alignment`` when a benchmark was given);
an oversized result is thinned and marked ``truncated_by_mcp``. If
the engine rejects the request as invalid (400/422), returns
{"accepted": false, "error": ...} so you can fix the named
field(s) and retry. Capacity, timeout, and permission failures
(e.g. 429/503/504/401/403) raise a tool error carrying explicit
recovery guidance.
输入模式
{'type': 'object', 'title': 'run_backtestArguments', 'required': ['data_source'], 'properties': {'include': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Include', 'default': None}, 'signals': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Signals', 'default': None}, 'strategy': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Strategy', 'default': None}, 'benchmark': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Benchmark', 'default': None}, 'execution': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Execution', 'default': None}, 'data_inputs': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Data Inputs', 'default': None}, 'data_source': {'type': 'object', 'title': 'Data Source', 'additionalProperties': True}, 'trades_limit': {'type': 'integer', 'title': 'Trades Limit', 'default': 50}, 'response_detail': {'enum': ['summary', 'stats', 'full'], 'type': 'string', 'title': 'Response Detail', 'default': 'summary'}}}
输出模式
{'type': 'object', 'title': 'run_backtestDictOutput', 'additionalProperties': True}
search_tickers
Search available assets by ticker or name (relevance-ranked).
Use to resolve a user's asset mention ("bitcoin",
"S&P") to the exact ticker before requesting a server-side data fetch.
asset_class filters to 'stocks', 'crypto', 'forex', or 'indices'.
输入模式
{'type': 'object', 'title': 'search_tickersArguments', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 20}, 'query': {'type': 'string', 'title': 'Query'}, 'asset_class': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Asset Class', 'default': None}}}
输出模式
{'type': 'object', 'title': 'search_tickersDictOutput', 'additionalProperties': True}
validate_strategy
Validate a strategy document without running a backtest.
A cheap quota separate from backtest runs,
so validate freely and ALWAYS before run_backtest.
Args:
strategy: The strategy document â name, indicators[], and
condition_tree (see get_strategy_schema for the exact shape).
injected_indicators: Names of custom time-series columns the
caller will supply via data_inputs at run time, so conditions
referencing them validate.
Returns:
On success: {"valid": true, "warmup_bars": ..., referenced
indicators/columns}. On failure: {"valid": false, "errors": [...]}
where each error carries a machine code, the location in the
document, a message, and context (e.g. the list of valid column
names). A failed validation is a NORMAL result, not an error â
read the errors, fix the document, and validate again before
running.
输入模式
{'type': 'object', 'title': 'validate_strategyArguments', 'required': ['strategy'], 'properties': {'strategy': {'type': 'object', 'title': 'Strategy', 'additionalProperties': True}, 'injected_indicators': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Injected Indicators', 'default': None}}}
输出模式
{'type': 'object', 'title': 'validate_strategyDictOutput', 'additionalProperties': True}
历史
近期工具变更
已添加
get_macro_series
2026年9月17日 12:33
已添加
list_macro_series
2026年9月17日 12:33
已添加
get_price_history
2026年9月17日 12:33
已添加
get_quote
2026年9月17日 12:33
已添加
get_ticker_info
2026年9月17日 12:33
已添加
get_data_range
2026年9月17日 12:33
已添加
list_tickers
2026年9月17日 12:33
已添加
search_tickers
2026年9月17日 12:33
已添加
compute_stats
2026年9月17日 12:33
已添加
export_backtest
2026年9月17日 12:33
已添加
compare_backtests
2026年9月17日 12:33
已添加
get_latest_signal
2026年9月17日 12:33
已添加
run_backtest
2026年9月17日 12:33
已添加
validate_strategy
2026年9月17日 12:33
已添加
get_strategy_schema
2026年9月17日 12:33
已添加
list_templates
2026年9月17日 12:33
已添加
list_indicators
2026年9月17日 12:33
已添加
get_catalog
2026年9月17日 12:33
已添加
engine_info
2026年9月17日 12:33
已添加
get_me
2026年9月17日 12:33
发现
类似的 MCP 服务器
AlpineDataWorks Intelligence Server
com.alpinedataworks/adw-intelligence-server
Provides economic, market, supply-chain, real-estate, energy, consumer, labor, and other scored intelligence indices with histori…
Stratalize Finance
com.stratalize/finance
Provides financial, macroeconomic, banking, credit, commodities, M&A, ESG, labor, and regulatory benchmarks for analysis and plan…
Valuein — SEC EDGAR Fundamentals & Smart-Money Data
io.github.valuein/mcp-sec-edgar
Provides point-in-time SEC EDGAR fundamentals, filings, ownership signals, financial analysis, valuation models, research reports…
equibles
io.github.daniel3303/equibles
Provides equity and market research tools covering SEC filings, company financials, portfolios, prices, options, macroeconomic da…
DFX Real Estate Intelligence
io.github.Capital-W-Holdings/us-property-parcel-real-estate-debt
Provides US commercial real estate, parcel, debt maturity, bank CRE exposure, private capital, investor, ownership, occupancy, an…
simplefunctions
io.github.spfunctions/simplefunctions
Provides prediction-market data, thesis analysis, market signals, portfolio tracking, and automated intent-based trading workflow…
EventTrader MCP
com.cymetica/event-trader-mcp
Provides prediction-market research and trading capabilities, including real-time event-market data, CLOB execution paths, fund i…
Signal8
ai.signal8/mcp
Provides SEC filings, dilution data, insider and institutional ownership, and political-trade data.