M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
T

TVScreener MCP Server

Community
Unofficial TradingView Screener data access via MCP, supporting stocks, crypto, forex, bonds, futures, and coins.
How to install ↓ Compare GitHub source repository ↗
Category
Other
Stars
★ 1.6k Very popular
Transport
stdio (local process)
Runtime
Python
Credentials
No credential needed
License
Apache-2.0
Last commit
Tools
6
42FMRS · D

tvscreener is a powerful unofficial TradingView Screener MCP server offering comprehensive fields and flexible filtering, but given its unofficial nature, users should be aware of data reliability and compliance risks.

Strongest · Documentation 12/20 Weakest · Reliability 6/20

Reliability
6/20
Security and permissions
6/20
Maintenance
8/20
Documentation
12/20
Setup experience
10/20
Why each score
Reliability 6/20
Static review could only rely on README claims about MCP integration; no manifest or executable evidence was supplied. We cannot verify a clean init/tool-list handshake, and no tests or error-handling details are present. Following the 'missing evidence is a deduction' rule, reliability is scored 6.
Security and permissions 6/20
The source cannot be audited for malicious behavior, and no credential handling is documented. The library makes external network requests to TradingView, but the README does not disclose data boundaries or least-privilege design. No red-line issue is evident, but the absence of audit evidence reduces the score to 6.
Maintenance 8/20
The repository is not archived, has an Apache-2.0 license, and the README references v0.1.0/v0.2.0 releases and CI/coverage badges. However, there are no commit dates, release dates, or issue-response records in the provided evidence, so maintenance is scored 8.
Documentation 12/20
The README is thorough for the Python library, with installation, fluent API, field discovery, presets, and streaming examples. For MCP, it gives only a brief tool list and registration commands without parameter details or troubleshooting, so documentation scores 12.
Setup experience 10/20
Setup is described in a few clear steps: pip install with the MCP extra, run tvscreener-mcp, and a Claude Code registration example. However, there are no examples for other clients and no verification that the connection works, so setup scores 10.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Quantitative analysts and traders who need quick access to TradingView Screener data.
  • Developers who want to integrate market data into AI workflows.

Not for

  • Use cases requiring an official data source or real-time trading execution.
  • Production environments with high reliability requirements or guaranteed data stability.

Required permissions

  • Requires network access to request TradingView Screener.
  • May need to read local configuration files to persist user settings.

Risks and side effects

  • Unofficial APIs may change without notice, causing malfunction or inaccurate data.
  • Potential violation of TradingView's Terms of Service, with legal risks.
  • High query frequency could lead to IP restrictions or bans.
  • Data is for reference only and does not constitute investment advice.

Setup

Before you start

Runtime：Python

Install the Python package: pip install 'tvscreener[mcp]'. Then run the MCP server: tvscreener-mcp. Register with Claude Code: claude mcp add tvscreener -- tvscreener-mcp.

Check that it works

After running 'claude mcp add tvscreener -- tvscreener-mcp', the tools discover_fields, custom_query, search_stocks, search_crypto, search_forex and get_top_movers should appear in your client's tool list; calling get_top_movers and receiving market data confirms the connection.

Troubleshooting

  1. Verify network connectivity and access to TradingView.
  2. Check Python environment and dependencies are fully installed.
  3. If a query fails, try reducing filter criteria or update to the latest version.
  4. If rate-limited, increase query intervals or use the interval parameter in streaming updates.

Things to try

Once connected, you can ask your AI assistant things like:

  • Search for RSI-related fields available in the stock screener
  • Find the top gainers and losers in the crypto market right now
  • List US stocks priced above $50 with volume over 1 million
  • Show me the major forex pairs and their percent changes today

Tools 6

discover_fields read-only
Search available fields by keyword, returning a list of matching fields.
custom_query read-only
Execute flexible queries with any fields and filters, returning a data frame.
search_stocks read-only
Simplified stock screener with common filters, returning stock data.
search_crypto read-only
Simplified cryptocurrency screener, returning crypto data.
search_forex read-only
Simplified forex screener, returning forex pair data.
get_top_movers read-only
Get a list of top gainers and losers.

Use cases

Retrieve real-time stock, crypto, and other market data via an AI assistant.
Perform custom market screening based on 13,000+ fields.
Monitor market trends and get top movers.

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

tvscreener is a third-party Python library and MCP server that allows AI assistants to access public data from TradingView's screener. It supports six screener types (Stock, Crypto, Forex, Bond, Futures, Coin) with over 13,000 fields, and offers Pandas DataFrame output, streaming updates, and type-safe validation. The MCP server provides tools to discover fields, execute custom queries, and use simplified screeners for stocks, crypto, and forex.

Similar servers

Telegram MCP Server 70 · B

Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.

★ 1.8k · Tools 76 Compare with this →
Compare with other MCP servers

Source revision 6faf496fa8b2 Data synced 2026-10-12 Read the FMRS scoring method