tv-history
MCP server for historical asset analysis using tvDatafeed and cached CSV files. Enables fetching OHLCV bars, candlestick charts, and trade execution data for TradingView-style assets.
README
tv-history MCP
Standalone historical asset-analysis MCP server backed by tvDatafeed and local timeframe-specific CSV files.
Assets are loaded dynamically. TradingView-style EXCHANGE:SYMBOL is preferred,
for example RUS:MX1!. The existing SYMBOL:EXCHANGE format remains accepted
for backward compatibility. A valid request triggers an initial tvDatafeed
download when no local history exists for that asset and timeframe.
Install and run
cd C:\_tools\202607_tradingview_mcp\tv_history
uv sync
uv run tv-history-mcp
HTTP transport:
uv run tv-history-mcp streamable-http --host 127.0.0.1 --port 8010
The MCP endpoint is http://127.0.0.1:8010/mcp.
Codex registration for the HTTP server:
codex mcp add tv-history --url http://127.0.0.1:8010/mcp
Or let Codex launch the stdio server:
codex mcp add tv-history -- C:\_tools\202607_tradingview_mcp\tv_history\.venv\Scripts\python.exe -m tv_history.server
Tool
asset_analysis(
asset="BITSTAMP:BTCUSD",
timeframe="1h",
timestamp="2026-07-01T12:00:00Z"
)
The default legacy response remains available for existing callers. Request
the compact, completed-bar-only trading response explicitly:
asset_analysis(
asset="BITSTAMP:BTCUSD",
timeframe="4h",
timestamp="2026-07-01T12:00:00Z",
response_version="execution",
include_short_term=true,
short_term_sessions=4
)
asset_bars(
asset="ICEEUR:BRN1!",
timeframe="1h",
timestamp="2026-03-23T00:00:00Z",
sessions=4
)
asset_bars returns completed OHLCV bars oldest-first. Use count (1–1000)
or sessions; when both are supplied, sessions wins.
asset_chart(
asset="BITSTAMP:BTCUSD",
timeframe="4h",
timestamp="2026-07-01T12:00:00Z",
days="10"
)
asset_chart returns a PNG candlestick chart with red/green bodies, wicks, and
volume, plus a compact metadata block describing the asset and chart range.
Use sessions instead of days to request a fixed number of trading dates;
sessions wins when both are supplied. All tool errors use the same structured
error object and are marked as MCP errors.
Supported timeframes are 1h, 4h, 1D, and 1W. Each timeframe is fetched
directly from tvDatafeed and stored independently as 1h.csv, 4h.csv,
1D.csv, or 1W.csv. Analysis and charts read the requested timeframe file;
they do not construct higher-timeframe bars from 1h.csv.
An empty timeframe store requests up to 5,000 bars. A subsequent request refreshes only when its timestamp is later than the latest stored timestamp for that timeframe. The refresh size is the estimated number of missing bars plus 10 overlapping bars, capped at 5,000. New and old rows are merged by timestamp, with fresh provider values winning.
Provider failures are retried five times with a five-second wait between attempts. Attempts 1–3 use the original request capped at 5,000 bars, attempt 4 caps it at 4,000, and attempt 5 caps it at 2,000.
Every triggered provider download is appended to data/download_control.csv.
The control rows contain asset, timeframe, requested_at, bars_requested,
status (success or failure), and the UTC input_timestamp. Existing rows
from the older schema are preserved with a blank timeframe because it cannot be
inferred reliably. Requests already covered by local data do not trigger a
download and are not logged.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。