TickerDB

com.tickerdb由 tickerdb.com 发布官方发布者v1.8.6更新于 Oct 24, 2026

Pre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines.

已验证Streamable HTTP可网页运行金融数据与分析

概览

AI 生成的概览

TickerDB 让助手直接读取预先计算好的股票、ETF 与加密货币市场状态、筛选器、OHLCV 历史与自选列表工具,无需自行计算指标。

可以做什么
  • 查询单个标的的预计算市场情报:最新快照、历史快照或序列,以及状态出现后通常的后续表现
  • 获取日线或周线收盘 OHLCV K 线,用于收益计算、图表与回测
  • 按分类状态筛选资产或按字段排序,并查看字段与区间取值的结构说明
  • 读取自选列表的汇总与字段级变化,并按请求添加或移除标的
  • 查询账户套餐、额度上限与用量
适用场景
适合需要让助手基于“超卖”“强上升趋势”等命名状态分析美股、ETF 或加密货币、筛选交易形态,或汇报自选列表当日变化的场景,而不必从原始 K 线自行计算指标。
运行要求
可使用托管 Streamable HTTP 端点(OAuth 或 Bearer 令牌),或通过 npx 运行本地 npm 包 tickerdb-mcp。本地包需要 TickerDB API 密钥,通过环境变量 TICKERDB_KEY 提供;套餐等级决定额度上限与历史深度。
安装前请注意
API 密钥属于机密,不应写入共享配置。用量按额度与套餐计量,大量筛选或历史查询可能消耗配额或产生超额费用。添加与移除自选列表的工具会修改账户中保存的数据,移除操作可撤销。

安装

在 SourceWeft 中

  1. 打开 控制台中的 TickerDB,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.tickerdb%2Fmcp-server/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "tickerdb": {
      "type": "http",
      "url": "https://mcp.tickerdb.com/mcp"
    }
  }
}

README

TickerDB — Stock market data for agents.

Pre-computed stock market data for AI agents. TickerDB returns indicators like trend_direction, support_level, and analyst_consensus as named states — plus what changed and what usually happens next.

10,000+ US stocks, ETFs, and crypto pairs · 182 indicators across trend, momentum, volatility, volume, patterns, support/resistance, fundamentals, and sector context · 7 years of history · tickerdb.com

Tools

ToolDescription
get_summaryTechnical + fundamental snapshot for a ticker. Historical lookups, state transition history, and what usually happens after
get_ohlcvDaily or weekly EOD candles for returns, charts, and backtests
get_searchScreen assets by categorical state or rank by fields like market_cap or pe_ratio
get_schemaDiscover every field (ticker level and market level) and its valid band values
get_marketMarket and macro regime bands (market_, macro_): latest, history, regime changes; combine with get_search to screen tickers under a regime
get_changesWhat changed on the newest date for up to 50 tickers — day-over-day or week-over-week
get_universeSelected fields for every asset on one date, in one call (trading-model input)
get_insidersFind insiders (CEOs, directors, 10% owners, funds) by name, ticker or role
get_insider_tradesOne insider's disclosed trades by disclosure time (copy/inverse insider models)
get_fundsFind ETFs and mutual funds that file SEC N-PORT holdings, by name or ticker
get_fund_holdingsA fund's full portfolio as public on a date (point in time by filing date)
get_fund_holdersWhich funds held a stock on a date, plus its tracked index memberships
get_indexesTracked indexes (S&P 500/400/600/100, Nasdaq-100, Russell 1000/2000) and their source funds
get_index_membersAn index's members on a date (point in time; also member_of in get_universe/get_search)
get_statusWhen data was last released (daily/weekly, preliminary or final): poll this, not ticker tools
get_accountAccount details, plan tier, and usage

All tools are available on every tier (Free, Plus, Pro). Tiers differ by credit limits, history depth, and number of filters. See tickerdb.com/pricing.

Quick start

Connect TickerDB to Claude, ChatGPT, or another MCP client (see Setup below), then try:

"Show me oversold large-cap stocks near support"

The agent calls get_search with filters for momentum_rsi_zone = oversold and market_cap_tier in [large, mega], then follows up with get_summary on individual results. No raw number crunching — the agent reads categorical states and reasons over them directly.

"What usually happens when AAPL goes oversold?"

get_summary with field=momentum_rsi_zone, band=oversold, stats=true returns aggregate aftermath distributions: how the stock performed 5, 10, 20, 50, and 100 days after each oversold entry over 7 years of history.

"What changed for AAPL, MSFT and NVDA today?"

get_changes returns only the field-level state transitions of the newest date — band entries, exits, and shifts — so the agent reports what moved without pulling full summaries for every ticker.

Why not just pass raw OHLCV?

A model can compute RSI from raw bars. But ask "Does AAPL look bullish?" with raw OHLCV and it burns its context on arithmetic — computing indicators one by one — instead of doing what you actually asked: noticing that RSI just hit oversold while institutions are accumulating, that the pullback is sharp but the 200-day uptrend is intact, that insiders have been selling all quarter. That's the analysis. Raw bars bury it under computation.

With TickerDB, the model sees "oversold", "accumulation", "strong_uptrend" and connects them immediately.

State transitions go further. "What happened the last time BTC was this oversold?" means computing RSI across 7 years of daily bars, finding every oversold entry, and calculating what happened after each one. With TickerDB it's one call: get_summary with field=momentum_rsi_zone, band=oversold, stats=true.

Setup

Hosted server (recommended)

The remote server at https://mcp.tickerdb.com/mcp supports OAuth 2.1 and Bearer token auth. Use Streamable HTTP transport (not legacy SSE).

ClientHow
Claude.aiSettings → Connectors → Add → https://mcp.tickerdb.com/mcp → Authorize
Claude Codeclaude mcp add --transport http --scope user tickerdb https://mcp.tickerdb.com/mcp
ChatGPTPlugins → + → https://mcp.tickerdb.com/mcp → Create → Authorize
Cursor.cursor/mcp.json → {"tickerdb": {"url": "https://mcp.tickerdb.com/mcp"}}
Any MCP clientStreamable HTTP to https://mcp.tickerdb.com/mcp with Authorization: Bearer tdb_...

npm package (local stdio)

For clients that prefer a local process (Claude Desktop, etc.):

json
{  "mcpServers": {    "tickerdb": {      "command": "npx",      "args": ["tickerdb-mcp"],      "env": {        "TICKERDB_KEY": "tdb_your_api_key_here"      }    }  }}

Get an API key at tickerdb.com/dashboard.

Structure

Three-package monorepo:

  • shared/ — Tool definitions, API client, and server factory (internal)
  • remote/ — Cloudflare Worker at mcp.tickerdb.com (Streamable HTTP + OAuth 2.1)
  • local/ — Published npm package tickerdb-mcp (stdio)

Both transports use the same tool definitions. The MCP server is a thin proxy — access control, rate limiting, and field filtering are handled by the TickerDB API.

Authentication

  • Bearer token — Authorization: Bearer tdb_...
  • OAuth 2.1 — dynamic client registration, PKCE, token exchange, revocation. /authorize redirects to tickerdb.com for consent.

Unauthenticated initialize and tools/list are permitted for tool discovery; tools/call requires auth and returns a 401 Bearer challenge with resource_metadata for clean re-authorization.

Session strategy

The remote worker defaults to stateless transport — intentionally. All tools are request/response stateless, and Cloudflare Worker memory is isolate-local. Stateless mode avoids edge session loss that can invalidate connector-discovered namespaces. Set MCP_SESSION_MODE=stateful for explicit session debugging.

Development

bash
npm install                              # workspace dependenciesnpm run build                            # type-check remote + sharednpx wrangler dev                         # remote dev servercd local && npm install && npm run build  # npm package

Deployment

bash
# Remote servernpx wrangler deploy
# npm + MCP Registry (recommended)export MCP_PUBLISHER_KEY="your_saved_tickerdb_registry_private_key_hex"./release.sh mcp patch
# npm onlycd local && npm version patch && npm run build && npm publish

来源:README.md,提交 1b2e0b0

工具

9

get_summary

Get pre-computed market intelligence for a specific stock, crypto, or ETF ticker. Supports 4 modes: (1) Snapshot (default) for the latest categorical state; (2) Historical snapshot by date; (3) Historical series with start and end dates; (4) Events by field and optional band, including aftermath fields on paid tiers, weekly trend_stage analysis, pattern setup states such as pattern_bull_flag and pattern_ascending_triangle, MA signal fields, trend_ma_crossover_event, MA distance lookbacks such as trend_distance_ma40, and stock-only fundamentals_free_cash_flow events. Add stats=true in event mode to return aggregate event-band and aftermath distributions instead of raw rows. Results can include freshness via as_of_date, same-candle OHLCV, market_cap, market_cap_tier, trend, momentum (including raw rsi, stochastic_k, stochastic_d alongside their zones, divergence_detected, divergence_type, stochastic_zone), volatility (including squeeze_active, squeeze_days), volume (including climax_detected, climax_type), patterns, support/resistance, levels (paid tiers), sector_context (rsi_zone, trend, agreement, asset_vs_sector_rsi), and stock-only fundamentals such as raw pe_ratio (latest ratio on or before the snapshot date; negative values preserved and unavailable values null), free_cash_flow, growth_zone, earnings_proximity, earnings_proximity_basis, analyst_consensus, valuation_percentile, and nested insider_activity when available. Raw momentum values (momentum.rsi 0-100, momentum.stochastic_k, momentum.stochastic_d) are the exact numbers behind their zones for all asset classes and both timeframes, null while lookbacks form; query zone transitions via momentum_rsi_zone / momentum_stochastic_zone, not the raw values. Summary keeps sibling _meta objects off by default; set meta=true or request explicit *_meta fields when paid-tier stability metadata is needed.

输入参数endbanddatemetaafterfieldlimitstartstatsbeforefieldssample另有 5 个

get_ohlcv

Get stored end-of-day OHLCV candles for a stock, ETF, or crypto ticker, daily or weekly. Use this for exact-return calculations, charts, and backtests after get_summary identifies a setup. Results are paginated; pass next_cursor back as cursor to continue. Equity and ETF bars are split-and-dividend adjusted; crypto bars are unadjusted. Credit cost is 1 credit per 100 bars returned, rounded up, with a 1 credit minimum.

输入参数endlimitorderstartcursorticker必填timeframe

get_schema

Get the schema of all available fields and their valid band values. Use this when the user asks 'what fields are available?', 'what bands does momentum_rsi_zone have?', 'what sectors exist?', or when you need to validate field/band names before calling get_summary with event parameters or get_search with filters.

无需输入参数。

get_account

Get your account details including current plan tier, monthly credit limits, and current usage. Response includes tier, limits (monthly_requests, overage_enabled, watchlist_limit, search_results, webhook_urls, history_days), and usage (monthly_requests_used, monthly_requests_remaining, credit_balance for pay-per-use accounts). Also returns scheduled_tier and scheduled_change_at if a plan change is pending.

无需输入参数。

get_watchlist

Get analytical summaries for every ticker on the user's saved watchlist. This supports requests about the user's watchlist, tracked stocks, portfolio tickers, or an overview of tracked assets. Each item includes trend, momentum, volatility, volume, extremes, support/resistance prices, and a notable_changes array of human-readable day-over-day change alerts (e.g. 'entered deep_oversold', 'volume spike', 'trend reversed to downtrend', 'earnings within days', 'squeeze activated', 'MA crossover: golden cross'). Additional per-item fields include squeeze_active, squeeze_days, climax_detected, climax_type, divergence_detected, divergence_type. Plus/Pro plans also return analyst_consensus, earnings_proximity, growth_zone, free_cash_flow. Pro plans also return insider_activity and insider_net_direction. Band fields include _meta stability objects on Plus and Pro plans. Use this only for questions that span the whole tracked set; for a question about one specific ticker use get_summary instead, even if that ticker is on the watchlist. When the question is only whether anything changed, prefer get_watchlist_changes: it returns just the deltas, whereas this returns a full summary per ticker and grows large on a watchlist of many assets. Use add_to_watchlist to save tickers first; an empty watchlist means the user has not saved any tickers yet, not that the lookup failed.

无需输入参数。

get_watchlist_changes

Get field-level state changes for all tickers on the user's saved watchlist since the last pipeline run. Supports daily day-over-day and weekly week-over-week comparisons. Each change object includes stability metadata such as stability, periods_in_current_state, flips_recent, and flips_lookback when available. Stability metadata requires a Plus or Pro plan. Prefer this over get_watchlist for monitoring questions such as whether anything moved, turned bearish, or became overbought, and for tracking a watchlist over time: it returns only what changed, while get_watchlist returns full summaries for every tracked ticker and is far larger on a big watchlist. Use get_watchlist when the current state of the whole list is needed rather than just the deltas. This is the only way to get week-over-week changes; the notable_changes array on get_watchlist is day-over-day only.

输入参数timeframe

add_to_watchlist

Add tickers to the user's saved watchlist. Duplicates are skipped. Only call this when the user explicitly asks to track, save, or watch a ticker; do not add tickers just because they came up in conversation. The watchlist is capped by the plan's watchlist_limit (see get_account), so the request can be rejected or accepted only in part. Report back which tickers the response actually confirms rather than assuming every requested ticker was added.

输入参数tickers必填

remove_from_watchlist

Remove tickers from the user's saved watchlist. Only call this when the user explicitly asks to stop tracking, remove, or drop a ticker; never prune the watchlist on your own initiative. Removal only stops tracking and can be undone with add_to_watchlist.

输入参数tickers必填

版本历史

1
  1. v1.8.6最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分