LABSCO SUMMARY

Same question, three sources, three different answers — and that is the useful part.

The project's own example shows one query returning 2201 rows on one site and 100 on the others, with completely different top results, which is exactly why having all three behind one interface beats trusting any single screener. Set a long client timeout: opening a browser and paging through results takes far longer than an API call, and the recommended value in the sample config is 300 seconds.

What it is

A Playwright-driven server that types a natural-language screening query into a finance site, intercepts the response, and returns the result table. Three sources are supported, so if one site is down or changes its layout you switch to another.

What you get

Screening queries against Tonghuashun iWenCai, Tongdaxin Wenxiaoda, and Eastmoney's conditional stock screener
Query types covering stocks, ETFs, funds, indices and sector boards
Results as a table you can take away in markdown or CSV form
A second mode that drives web chat providers — Nami Search, Tencent Yuanbao and Baidu AI Search — and returns clean text instead of broken copy-paste
Three transports: stdio, sse and streamable-http on a port you choose

Requirements

pip install mcp_query_table, plus a Chrome browser it can drive — either an already-running instance reached over the debugging port, or a headless one launched with an explicit user data directory. Log in to any site you have an account with beforehand; there is no automatic login. Keep the browser window wide enough that sites do not switch to their mobile layout, or table extraction fails.

Setup effort

One command — pip install -i https://pypi.org/simple --upgrade mcp_query_table

See installation options

USE CASES

01

Screening in plain language instead of building a filter

Ask the question in one sentence and get the ranked table, without learning each site's query builder.

02

Cross-checking a screen before you act on it

Run the same query against a second source and compare — the differences tell you how the sites read your wording.

03

Keeping the model from splitting your query

Quote the condition and name the source in the request, so a compound screen is not silently broken into two lookups.

04

Switching sources when a site changes

Point the same query at another site rather than waiting for a scraper fix.

BEFORE YOU INSTALL

What to know first

Requires

Python 3.10+
Chrome for it to drive (Edge works only after every Edge process is closed)
If you have accounts on the finance sites, sign in to them in that browser beforehand — the tool does not log in for you

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

pip install -i https://pypi.org/simple --upgrade mcp_query_table

MCP Clients

Cline

CLINE · JSON

{
  "mcpServers": {
    "mcp_query_table": {
      "timeout": 300,
      "command": "python",
      "args": [
        "-m",
        "mcp_query_table",
        "--format",
        "markdown",
        "--endpoint",
        "http://127.0.0.1:9222",
        "--executable_path",
        "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
      ]
    }
  }
}

Query Table