de es fr ja ko ru zh

MCP TradingView Server

Name: MCP TradingView Server
Author: mathieubernardi

by mathieubernardi

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Servidor MCP TradingView

Servidor MCP (Model Context Protocol) en Python que expone los datos de mercado TradingView a un cliente MCP — Claude Desktop, claude.ai o cualquier otro cliente compatible. Los datos se obtienen mediante tvdatafeed (OHLCV) y tradingview-ta (screener).

Herramientas expuestas

Herramienta MCP	Descripción
`tv_get_historical_data`	Velas OHLCV históricas (acciones, cripto, forex, futuros)
`tv_get_quote`	Última vela + variación % respecto a la anterior
`tv_get_indicators`	Indicadores técnicos, contexto multi-timeframe y puntuación compuesta
`tv_screener`	Filtrado por mercado, volumen y RSI sobre un universo predefinido

`tv_get_indicators` en detalle

Indicadores calculados: RSI, MACD, Bollinger Bands (con detección de squeeze), EMA, SMA, ATR (con niveles de stop largo/corto), Estocástico, ADX (+DI/−DI), OBV, media y ratio de volumen de 20 períodos, y detección de divergencias RSI.

Tres opciones desactivadas por defecto:

Parámetro	Efecto
`include_weekly: true`	Añade un contexto semanal: `weekly_rsi`, `weekly_adx`, `weekly_trend`
`benchmark_symbol: "CW8"`	Calcula la fuerza relativa a 1 mes y 3 meses contra ese benchmark
`include_score: true`	Calcula una puntuación técnica compuesta en `[-1, +1]` y sus subpuntuaciones

Intervalos aceptados: 1, 3, 5, 15, 30, 45 (minutos), 1H, 2H, 3H, 4H, 1D, 1W, 1M.

Alcance del screener

tvdatafeed no expone una API de screener. Por tanto, tv_screener recorre un universo predefinido en código en MARKET_SYMBOLS (src/mcp_tradingview/client.py) y calcula los indicadores en cada símbolo mediante tradingview-ta:

Mercado	Universo cubierto
`france`	29 símbolos Euronext París — CAC 40, algunas midcaps tecnológicas, ETF elegibles PEA
`america`	20 blue chips Nasdaq / NYSE
`crypto`	8 pares principales de Binance
`forex`	6 pares principales

La enumeración ScreenerMarket también acepta futures, india, brazil, australia, canada, europe y hongkong, pero no hay ningún universo definido para esos mercados: la llamada devuelve una lista vacía. Añadir una entrada en MARKET_SYMBOLS basta para activarlos.

Related MCP server: tradingview-mcp

Arquitectura

Client MCP (Claude Desktop, claude.ai…)
    │
    ├── stdio ──► process local
    └── SSE   ──► serveur HTTP (Starlette + uvicorn)
              │
              ├──► tvdatafeed    : bougies OHLCV
              └──► tradingview-ta : screener
                        │
                        └──► cache TTL en mémoire

Requisitos previos

Python ≥ 3.11
Una cuenta TradingView es opcional: el acceso anónimo funciona, con límites de tasa más estrictos.
El SDK MCP está fijado en < 2.0.0: la versión 2.x elimina los decoradores @server.list_tools() / @server.call_tool() y renombra Tool.inputSchema a Tool.input_schema. Se necesita una migración antes de levantar este límite.

Instalación

git clone https://github.com/mathieubernardi/tradingview_mcp.git
cd tradingview_mcp

pip install -e ".[dev]"

cp .env.example .env   # puis éditer .env

Configuración

Todas las variables tienen el prefijo TV_ y pueden pasarse mediante un archivo .env o mediante el entorno.

Variable	Defecto	Descripción
`TV_TV_USERNAME`	(vacío)	Identificador de TradingView (opcional)
`TV_TV_PASSWORD`	(vacío)	Contraseña de TradingView (opcional)
`TV_TRANSPORT`	`stdio`	`stdio` o `sse`
`TV_HOST`	`127.0.0.1`	Host del servidor SSE
`TV_PORT`	`8765`	Puerto del servidor SSE (1024–65535)
`TV_DEFAULT_EXCHANGE`	`EURONEXT`	Bolsa por defecto si la llamada no la especifica
`TV_DEFAULT_N_BARS`	`500`	Número de velas por defecto
`TV_MAX_N_BARS`	`5000`	Límite del número de velas
`TV_CACHE_TTL_SECONDS`	`60`	Duración de vida de la caché en memoria (`0` = desactivada)
`TV_LOG_LEVEL`	`INFO`	`DEBUG`, `INFO`, `WARNING` o `ERROR`

El doble prefijo de TV_TV_USERNAME / TV_TV_PASSWORD es intencionado: el prefijo de entorno TV_ se añade a los campos tv_username / tv_password.

Iniciar el servidor

Dos puntos de entrada equivalentes: el script de consola mcp-tradingview y el módulo python -m mcp_tradingview. El segundo no depende del PATH, lo que lo hace más fiable en Windows.

# Linux / macOS — stdio
TV_TRANSPORT=stdio python -m mcp_tradingview

# Linux / macOS — SSE
TV_TRANSPORT=sse python -m mcp_tradingview

# Windows PowerShell — stdio
$env:TV_TRANSPORT = "stdio"; python -m mcp_tradingview

# Windows PowerShell — SSE
$env:TV_TRANSPORT = "sse"; python -m mcp_tradingview

Integración con Claude Desktop (stdio)

Añadir en claude_desktop_config.json — ~/Library/Application Support/Claude/ en macOS, %APPDATA%\Claude\ en Windows:

{
  "mcpServers": {
    "tradingview": {
      "command": "python",
      "args": ["-m", "mcp_tradingview"],
      "env": {
        "TV_TRANSPORT": "stdio",
        "TV_CACHE_TTL_SECONDS": "60"
      }
    }
  }
}

Si el entorno Python no es el predeterminado, reemplazar "python" por la ruta absoluta del intérprete del virtualenv. Para usar una cuenta de TradingView, añadir TV_TV_USERNAME y TV_TV_PASSWORD en el bloque env.

En modo stdio, la sesión de TradingView se establece de forma perezosa en la primera llamada a una herramienta: el handshake MCP responde inmediatamente y el cliente no sufre un timeout al iniciar.

Integración SSE

TV_TRANSPORT=sse TV_PORT=8765 python -m mcp_tradingview

Endpoint	Rol
`GET /sse`	Flujo SSE para declarar en el cliente MCP
`POST /messages/`	Canal de retorno de mensajes del cliente
`GET /health`	Sonda de vivacidad, devuelve `ok`

Desarrollo

pytest tests/ -v          # tests
ruff check src/ tests/    # lint
mypy src/                 # type checking (strict)

Limitaciones conocidas

tvdatafeed es un cliente no oficial que se apoya en los endpoints web de TradingView: puede dejar de funcionar sin previo aviso.
tv_screener no escanea un mercado completo, solo el universo predefinido descrito anteriormente.
Sin una cuenta Premium de TradingView, los datos pueden tener un retraso de varios minutos.
El acceso anónimo sufre límites de tasa considerablemente más estrictos que una cuenta conectada.
Los errores de una herramienta se devuelven al cliente en formato JSON {"error": ..., "tool": ..., "arguments": ...} en lugar de elevarse como errores de protocolo.

Estructura del proyecto

tradingview_mcp/
├── src/mcp_tradingview/
│   ├── __init__.py      # métadonnées du paquet (__version__)
│   ├── __main__.py      # entrée `python -m mcp_tradingview`
│   ├── config.py        # settings (pydantic-settings, préfixe TV_)
│   ├── models.py        # schémas Pydantic d'entrée / sortie
│   ├── client.py        # client TradingView, indicateurs, cache TTL
│   ├── tools.py         # définition JSON Schema + dispatch des outils
│   └── server.py        # serveur MCP (stdio + SSE) et entrée console
├── tests/
│   └── test_server.py
├── pyproject.toml
├── .env.example
├── .gitignore
├── LICENSE
└── README.md

Licencia

Distribuido bajo licencia MIT. Ver el archivo LICENSE.

Available Tools

4 tools

tv_get_historical_dataA

Fetch historical OHLCV (Open, High, Low, Close, Volume) bars for any symbol from TradingView. Supports stocks, crypto, forex, futures.

Name	Required	Description	Default
`n_bars`	No	Number of bars to return
`symbol`	Yes	Ticker symbol, e.g. 'BTCUSDT', 'AAPL', 'EURUSD'
`exchange`	No	Exchange name, e.g. 'EURONEXT' (PEA / Paris), 'NASDAQ', 'NYSE', 'BINANCE', 'FX'	EURONEXT
`interval`	No	Chart interval: 1, 3, 5, 15, 30, 45 (min) \| 1H, 2H, 3H, 4H \| 1D, 1W, 1M	1D

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral disclosure burden. It names the output content (OHLCV bars) and the supported asset classes, but it does not mention bar ordering, exchange-selection caveats for non-EURONEXT symbols, adjustment behavior, or error handling. Some useful transparency exists, but important nuances are omitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler. The primary action is front-loaded, and the second sentence adds useful asset-class scope without bloating the definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple and the schema documents all parameters, so an agent can invoke it. However, with no output schema and no annotations, the description leaves out useful invocation-relevant details such as whether exchange must match the symbol (the default is EURONEXT, which may not work for all symbols) and the ordering/shape of returned bars.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already documented. The description adds broad domain context ('Supports stocks, crypto, forex, futures'), but it does not add parameter-specific meaning beyond what the schema provides. The baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Fetch historical OHLCV bars for any symbol from TradingView.' This clearly distinguishes it from sibling tools like tv_get_quote, tv_get_indicators, and tv_screener, which serve different purposes (current quote, derived indicators, screening).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: use this tool when historical OHLCV candle data is needed. It does not explicitly say 'use tv_get_quote for current prices' or 'use tv_get_indicators for computed values,' but the historical bar framing makes the intended use apparent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

tv_get_indicatorsA

Compute technical indicators for any symbol. Includes RSI, MACD, Bollinger Bands (+ squeeze detection), EMA, SMA, ATR (+ stop levels), Stochastic, ADX (+DI/-DI), OBV, volume MA20/ratio, RSI divergence flags. Optional: weekly multi-timeframe context (include_weekly=true), relative strength vs benchmark (benchmark_symbol), composite technical score [-1,+1] (include_score=true).

Name	Required	Description	Default
`bb_std`	No
`n_bars`	No
`symbol`	Yes
`exchange`	No		EURONEXT
`interval`	No		1D
`bb_length`	No
`macd_fast`	No
`macd_slow`	No
`atr_length`	No
`indicators`	No
`rsi_length`	No
`ema_periods`	No
`macd_signal`	No
`sma_periods`	No
`atr_stop_mult`	No	ATR multiplier for stop_long / stop_short levels
`include_score`	No	Compute composite technical_score [-1,+1] and sub-scores
`include_weekly`	No	Fetch weekly bars for weekly_rsi, weekly_adx, weekly_trend
`benchmark_symbol`	No	Benchmark ticker for RS 1M/3M (e.g. 'CW8'). Empty = skip.
`benchmark_exchange`	No		EURONEXT
`divergence_lookback`	No	Bars window for RSI divergence detection

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden and does add useful behavioral context: RSI divergence flags, Bollinger squeeze detection, ATR stop_long/stop_short levels, the [-1,+1] composite score range, and what each optional flag produces. However, it does not reveal the return shape, that the indicators parameter defaults to ['all'] so every call computes the entire indicator set, or any data-source/error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences of roughly 60 words with the core purpose front-loaded and no filler. Parameter names are embedded inline (include_weekly=true, benchmark_symbol, include_score=true), making the text directly actionable for an agent without cross-referencing the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 20-parameter tool with no output schema and no annotations, the description thoroughly covers the feature and option matrix but omits the output contract: what the response contains, how weekly/benchmark/score fields appear in results, and that the default is to compute all indicators. An agent can select the tool confidently but would invoke it without knowing what it returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25%, so the description must compensate. It maps the three optional features to their parameter names inline (include_weekly=true, benchmark_symbol, include_score=true) and its indicator inventory aligns with the indicators enum values. The many numeric tuning parameters (macd_fast, atr_length, sma_periods, etc.) are left to their self-explanatory names, which is passable but adds no real semantic depth.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Compute technical indicators for any symbol') and enumerates the full indicator surface: RSI, MACD, Bollinger Bands with squeeze detection, EMA, SMA, ATR with stop levels, Stochastic, ADX, OBV, volume MA20/ratio, and RSI divergence flags. The sibling names (tv_get_historical_data, tv_get_quote, tv_screener) make this tool's distinct role unambiguous even without explicit comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The opening sentence establishes a clear selection context: use this tool when computed indicators are needed, as opposed to raw bars (tv_get_historical_data), a snapshot quote (tv_get_quote), or universe filtering (tv_screener). It stops short of naming those alternatives explicitly or stating when not to use this tool, but the purpose is specific enough that an agent can route correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

tv_get_quoteA

Get the latest price quote for a symbol: last OHLCV bar plus percentage change from the previous bar.

Name	Required	Description	Default
`symbol`	Yes	Ticker symbol
`exchange`	No		EURONEXT
`interval`	No		1D

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It usefully discloses the output shape (last OHLCV bar plus percentage change), but it does not mention data delay, exchange handling, or how the interval parameter affects the returned bar. Acceptable but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded, and free of filler. Every phrase earns its place by specifying the object, the timeframe, and the included data.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter read tool, the description gives the core return fields, but with no output schema and no annotations it should also clarify interval/exchange behavior and the reference period for the percentage change. Adequate with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%: only 'symbol' has a description, while 'exchange' and 'interval' are undocumented. The description adds no meaning for exchange or interval and does not compensate for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('get'), names the resource ('latest price quote for a symbol'), and states the exact payload ('last OHLCV bar plus percentage change from the previous bar'). The words 'latest' and 'last bar' clearly distinguish it from tv_get_historical_data and the other siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining a current snapshot rather than historical data or indicators, but it never explicitly states when to choose this tool over its siblings. There are no exclusions or alternative routing hints.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

tv_screenerA

Screen stocks, crypto or forex symbols by market, volume, RSI range. Markets include 'france' (Euronext Paris — PEA) and 'america' (Nasdaq / NYSE). Returns top matches with price, volume and RSI data.

Name	Required	Description	Default
`limit`	No
`market`	No	Market to screen: 'france' (Euronext Paris / PEA), 'america' (Nasdaq + NYSE), crypto, forex, futures, etc.	france
`max_rsi`	No
`min_rsi`	No
`min_volume`	No	Minimum volume filter
`min_market_cap`	No

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of explaining behavior. It does disclose output fields ('price, volume and RSI data') and the market coverage for France and America. It does not explain how 'top matches' are ordered, how limit interacts with results, or whether RSI bounds are inclusive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences that front-load the core purpose, then the key market values, then the return data. There is no filler or repetition of schema defaults.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an optional-parameter screener with no output schema, the description provides enough to invoke it sensibly: what it screens, key market options, and what data is returned. The missing ordering/ranking criteria and the unexplained min_market_cap parameter are gaps, but the tool remains usable with defaults.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, so the description must compensate. It adds the 'RSI range' concept and market context, but min_market_cap is completely unexplained and limit is only inferable. The description partially fills the gap but does not fully cover all six parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Screen') with a clear resource ('stocks, crypto or forex symbols') and names the key filtering dimensions. It also distinguishes itself from the sibling tools by focusing on screening/discovery rather than historical data, quotes, or indicators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied: use this tool to find symbols matching market, volume, and RSI criteria. However, it never explicitly says when NOT to use it or directs the agent to alternatives like tv_get_quote or tv_get_indicators, so routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.1.0Sep 6, 2026
- First observedtv_get_historical_data
- First observedtv_get_indicators
- First observedtv_get_quote
- First observedtv_screener

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-09-06 00:15 across 4 tools

Disambiguation5/5

Each tool targets a distinct data need: historical bars, latest quote, indicator calculation, and symbol screening. The only potential overlap is RSI appearing in indicators and screener, but the intended use (computing vs scanning) is clear.

Naming Consistency4/5

Three tools follow the `tv_get_*` verb-object pattern and all use consistent snake_case with a `tv_` prefix. `tv_screener` is the outlier because it uses a noun instead of an action verb, but it is still recognizable within the family.

Tool Count5/5

Four tools is a reasonable, focused size for a market-data server, and each tool provides broad functionality (multi-symbol historical data, quotes, many indicators, and a screener). None feels redundant or unnecessary.

Completeness4/5

The server covers the core market-data workflow: retrieving history, checking current prices, computing technical analysis, and discovering symbols via screening. Minor gaps such as no dedicated symbol-search or fundamental data endpoint exist, but they are workable around for typical technical-analysis use cases.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

Related MCP Connectors

Marketdata App A
io.github.pipeworx-io
Market Data App MCP — wraps the Market Data App API (marketdata.app)
Finance Cryptocurrency
481
https://gateway.pipeworx.io/marketdata-app/mcp
Cryptohopper Market DataOAuth
com.cryptohopper
Real-time crypto market data: candles, tickers, orderbooks across 13+ exchanges via MCP.
Cryptocurrency Finance
2
https://mcp-data.cryptohopper.com/mcp
sigrexOAuthDeprecated
io.sigrex
Create and manage trading strategies, bots, webhooks and signals from any MCP client.
Autonomous Agents
1
https://mcp.sigrex.io
FensoryOAuth
com.fensory
Trading MCP server for AI agents, with live market data, account reads and controlled execution.
Finance Cryptocurrency Blockchain
1
https://mcp.fensory.com/mcp

Related MCP Servers

tradingview-mcp
Finance Research & Data
pueschel88
A
license
Not graded
quality
C
maintenance
Enables MCP clients to control a local TradingView Desktop instance, providing tools to read chart state, change symbols and timeframes, and fetch OHLCV data.
Updated 2 months ago (2026-09-14 07:59 UTC)
120 npm
134
MIT
tradingview-mcp
Finance Cryptocurrency
GlynnCarson
A
license
B
quality
C
maintenance
TradingView MCP server — real-time market data, technical indicators, screeners, and backtesting for Claude, ChatGPT, Cursor, Copilot, and any MCP client. Stocks, crypto, forex & futures across global exchanges.
Updated 15 hours ago (2026-10-31 05:27 UTC)
44
1
MIT
TradingView MCP Server
Finance Search
S4consultoria
F
license
Not graded
quality
D
maintenance
Exposes TradingView data including quotes, technical ratings, historical OHLCV, and market screening through an MCP server using unofficial libraries.
Updated 3 months ago (2026-07-30 01:50 UTC)
-
tradingview-mesh
Finance Browser Automation
omnibot007
F
license
Not graded
quality
C
maintenance
Provides unified TradingView capabilities through one MCP server, including market data, screening, technical analysis, backtesting, sentiment, chart control via browser automation, Pine script transpilation and compilation, and alert webhooks.
Updated 2 months ago (2026-09-01 02:10 UTC)
-

Servidor MCP TradingView

Herramientas expuestas

tv_get_indicators en detalle

Alcance del screener

Arquitectura

Requisitos previos

Instalación

Configuración

Iniciar el servidor

Integración con Claude Desktop (stdio)

Integración SSE

Desarrollo

Limitaciones conocidas

Estructura del proyecto

Licencia

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

`tv_get_indicators` en detalle