Compound Interesting — market intelligence
Source-backed US market signals: insider filings, Congress trades, institutions, consensus.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"market-intelligence": {
"url": "https://api.compoundinterest.ing/mcp"
}
}
}远程端点
https://api.compoundinterest.ing/mcpstreamable-http它能做什么
工具清单
工具(16)
🟢get_composite(ticker)
Everything the platform knows about one ticker in a single record: the cross-signal consensus, each contributing dimension with its direction and provenance, and risk flags. Start here for any question about a specific company.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢get_demo_composite
A single fixed demo ticker, callable without an API key, so the data shape can be inspected before signing up. Returns only the demo ticker regardless of input. For real tickers use get_composite, which requires a free key.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_evidence(ticker)
Paid key required. The primary documents a ticker's signals were derived from — insider Form 4s, institutional holdings and macro series, with the filing each came from where one is available. Use this to cite a claim rather than assert it. Paid keys are not on sale yet. A ticker whose evidence has not been published yet returns evidence_not_published. Congressional trades are not included: use list_congress_trades, which works on every key.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢get_house_rating(ticker)
Paid key required. The platform's own buy/hold/sell rating for a ticker, with the reasoning behind it. A judgement about the stock, not a recommendation to any reader. Paid keys are not on sale yet.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢get_consensus(ticker)
Whether the independent actors this platform tracks — insiders, Congress, institutions, the model — agree on one ticker, with the per-dimension breakdown that produced the verdict.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢rank_consensus(direction, min_agreement, min_signals, limit)
The names where independent actors agree most strongly, ranked. Use this to find candidates rather than to check one you already have in mind.
输入模式
{
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": [
"bullish",
"bearish",
"mixed",
"neutral"
],
"description": "Restrict to one consensus direction."
},
"min_agreement": {
"type": "number",
"description": "Minimum agreement score, 0-1."
},
"min_signals": {
"type": "integer",
"description": "Minimum number of dimensions that voted."
},
"limit": {
"type": "integer",
"description": "How many rows to return."
}
},
"additionalProperties": false
}🟢screen(sector, rating, state, min_confidence, min_completeness, ...)
Filter the whole equity universe and return matching tickers with their scores. The bulk discovery tool: use it for questions of the form 'which companies have X'. To rank by cross-signal agreement instead, use rank_consensus.
输入模式
{
"type": "object",
"properties": {
"sector": {
"type": "string",
"description": "Restrict to one sector."
},
"rating": {
"type": "string",
"description": "Restrict to one house rating, e.g. buy, hold, sell. Requires a paid key."
},
"state": {
"type": "string",
"enum": [
"accumulation",
"distribution",
"event_driven",
"elevated_risk",
"mixed",
"quiet",
"activist_target",
"settlement_stress"
],
"description": "Restrict to one overall state."
},
"min_confidence": {
"type": "number",
"description": "Minimum model confidence, 0-1."
},
"min_completeness": {
"type": "number",
"description": "Minimum data completeness, 0-1."
},
"flagged": {
"type": "boolean",
"description": "Only entities with at least one event or risk dimension flagged (insider, material, macro, ftd, reporting_risk, ownership, news, ta, institutional, congress, fda_enforcement). Flags on fundamentals, macro_beta, narrative and gov_contracts do not count."
},
"sort": {
"type": "string",
"enum": [
"confidence",
"data_completeness",
"consensus_strength",
"house_rating_confidence"
],
"description": "Sort column. Defaults to confidence. house_rating_confidence requires a paid key."
},
"order": {
"type": "string",
"enum": [
"asc",
"desc"
],
"description": "Sort direction."
},
"limit": {
"type": "integer",
"description": "How many rows to return."
}
},
"additionalProperties": false
}🟢get_monthly_activity(kind, month)
Rank ticker activity aggregated from available published filings by transaction date for the current UTC month through today. Includes coverage metadata and unknown-value counts; this is not total market activity. Congress: 10 names on every customer key. Insiders: free keys receive up to 10 names, paid keys up to 20.
输入模式
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"insiders",
"congress"
],
"description": "Which published filing activity to aggregate."
},
"month": {
"type": "string",
"description": "Optional YYYY-MM; only the current UTC month is supported. Defaults to the current UTC month."
}
},
"required": [
"kind"
],
"additionalProperties": false
}🟢list_insider_trades(ticker, limit, cursor, since)
Corporate insider buys and sells from SEC filings, newest first, with a link to the filing each came from where one is available.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Restrict to one ticker, e.g. TSLA."
},
"limit": {
"type": "integer",
"description": "How many trades to return."
},
"cursor": {
"type": "string",
"description": "next_cursor from a previous call."
},
"since": {
"type": "string",
"description": "ISO date; only records on or after it."
}
},
"additionalProperties": false
}🟢list_congress_trades(ticker, limit, cursor, since)
Disclosed House and Senate trades, newest first, linked to the disclosure where one is available. Up to 20 rows per call on every customer key; page with next_cursor.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Restrict to one ticker, e.g. TSLA."
},
"limit": {
"type": "integer",
"description": "How many trades to return."
},
"cursor": {
"type": "string",
"description": "next_cursor from a previous call."
},
"since": {
"type": "string",
"description": "ISO date; only records on or after it."
}
},
"additionalProperties": false
}🟢list_positioning(ticker, limit, cursor, since)
Weekly speculative positioning in FUTURES markets from the CFTC Commitments of Traders report, newest first: net speculative position, its share of open interest and its historical percentile. Covers futures symbols such as ES (S&P 500 e-mini), GC (gold), ZT (2-year Treasury note), not individual stocks. Net figures can reflect hedges and cannot be read as a directional view on their own.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Futures symbol as the CFTC data stores it, e.g. ES, GC, ZT. Not an equity ticker."
},
"limit": {
"type": "integer",
"description": "How many records to return."
},
"cursor": {
"type": "string",
"description": "next_cursor from a previous call."
},
"since": {
"type": "string",
"description": "ISO date; only records on or after it."
}
},
"additionalProperties": false
}🟢get_historic_moves(ticker)
The historical distribution of 5-day and 1-month returns for a ticker, sampled over the last 5 years: mean, standard deviation, percentiles, a histogram, and the worst drawdowns with their dates. Use it to say whether a move is unusual FOR THIS NAME rather than in the abstract. Every number is a fraction: 0.0821 means 8.21%.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢list_equity_perp(limit)
Funding rate and open interest for the ~51 US single names listed on a 24/7 perpetual futures venue, ranked by notional. This is the ONLY source here that moves outside US market hours, so it is what to check overnight and at weekends. High positive funding means longs are paying to hold — crowded, squeeze-fragile. The mark price is a venue mark, NOT the stock price.
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "How many names to return."
}
},
"additionalProperties": false
}🟢get_equity_perp(ticker)
Funding and open interest for a single name on the 24/7 perpetual venue. Most tickers are NOT listed there — only about 51 of about 4,600 covered tickers — and a 'not listed' answer means no venue coverage, never that positioning is flat or zero.
输入模式
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker symbol, e.g. AAPL."
}
},
"required": [
"ticker"
],
"additionalProperties": false
}🟢search_tickers(query)
Resolve a company name or partial symbol to tickers the platform covers. Use this first when the user names a company rather than a symbol.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Company name or partial symbol."
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_signal(name)
A whole-market gauge rather than a per-company one. 'macro' is the market-regime read, 'energy' the macro energy balance, 'crypto' crypto positioning and funding, 'rate_expectations' the market-implied path for policy rates. Use these for the backdrop a single name is trading against.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"enum": [
"macro",
"energy",
"crypto",
"rate_expectations"
]
}
},
"required": [
"name"
],
"additionalProperties": false
}社区
证据