Stockmatrix Mcp

io.github.MongLong0214Published by GitHub account MongLong0214v0.5.0Updated Oct 24, 2026

Korean stock market theme lifecycle analysis (TLI) — rankings, stock lookup, predictions & prompts

VerifiedSTDIODesktop onlyFinanceData & Analytics

Overview

AI-generated overview

Lets an assistant analyze Korean stock market investment themes using the TLI lifecycle score, with rankings, stock lookups, comparisons and predictions.

What you can do
Provides 11 tools over the StockMatrix API for Korean market theme analysis: theme rankings by lifecycle stage, an AI-optimized market summary, daily or weekly score movers and stage transitions, side-by-side comparison of two to five themes, and rise/peak/cool predictions based on historical analog matching. It also searches themes and stocks by keyword, name or six-digit code, performs reverse stock-to-theme lookup, returns detailed score breakdowns, 30-day score history, and TLI methodology documentation. Four workflow prompts bundle multi-tool analyses, and two read-only resources expose methodology and today's rankings.
When to use it
Useful when someone wants conversational insight into Korean equity themes rather than raw quotes: tracking which KOSPI/KOSDAQ themes are emerging or peaking, checking whether a held stock sits in a hot theme, comparing themes, or reviewing theme momentum over the past month.
Requirements
Runs locally as an npm package (stockmatrix-mcp) over stdio, launched with npx, so Node.js and network access to the StockMatrix API are needed. No authentication is declared. The optional environment variable STOCKMATRIX_API_URL overrides the default API base URL. Desktop MCP clients such as Claude Desktop, Cursor, Windsurf or VS Code are the documented targets.
Before you install
The server sends requests to the StockMatrix API and its data comes from third-party sources (Naver DataLab, Naver Finance, Naver News), so queries leave the machine. Setting STOCKMATRIX_API_URL to a non-default host redirects all traffic to that host. Output is analytical scoring and predictions, not investment advice, and no trading or write actions are exposed.

Installation

In SourceWeft

  1. Open Stockmatrix Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

stockmatrix-mcp

Official MCP server for StockMatrix (https://stockmatrix.co.kr).

Ask about Korean stock market themes in natural conversation with AI. Track 200+ KOSPI/KOSDAQ investment themes, get daily movers, look up which themes a stock belongs to, compare themes side-by-side, and see predictions — all through Claude, Cursor, or any MCP-compatible AI agent.

Powered by TLI (Theme Lifecycle Index) — a Bayesian-optimized scoring algorithm combining search interest, news momentum, market volatility, and stock activity into a 0-100 score with lifecycle stage classification.

11 tools + 4 one-click workflow prompts + live resources. Try the market_briefing slash command for an instant Korean market overview.

Quick Start

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "stockmatrix": {      "command": "npx",      "args": ["-y", "stockmatrix-mcp"]    }  }}

Cursor / Windsurf

Add to .cursor/mcp.json or .windsurf/mcp.json:

json
{  "mcpServers": {    "stockmatrix": {      "command": "npx",      "args": ["-y", "stockmatrix-mcp"]    }  }}

VS Code / Claude Code

Add to .vscode/mcp.json:

json
{  "servers": {    "stockmatrix": {      "command": "npx",      "args": ["-y", "stockmatrix-mcp"]    }  }}

Try Asking

After setup, just ask in natural language:

PromptWhat happens
"요즘 뜨는 테마 TOP 5"Top 5 themes ranked by TLI score
"오늘 한국 테마 시장 요약해줘"AI-optimized market overview
"어제 대비 가장 많이 오른 테마는?"Daily score movers and stage transitions
"AI 관련 테마 찾아줘"Search AI-related themes
"반도체 vs 2차전지 비교해줘"Side-by-side theme comparison
"앞으로 오를 테마 알려줘"Rising predictions with analog evidence
"삼성전자가 속한 테마"Stock-to-theme lookup (auto-detects 6-digit codes)
"방산 테마 상세 정보"Score breakdown, stocks, news, comparisons
"반도체 테마 최근 한달 추세"30-day score history
"TLI 점수는 어떻게 계산돼?"Algorithm methodology (tip: use section=scoring to save tokens)
"What are the hottest stock themes in Korea?"Works in English too

Available Tools

get_theme_ranking

Get theme rankings by lifecycle stage with limit and sort options.

ParameterTypeRequiredDescription
stagestringNoemerging / growth / peak / decline / reigniting
limitnumberNoResults per stage (1-50, default: 10)
sortstringNoscore / change7d / newsCount7d (default: score)

get_market_summary

Get an AI-optimized market overview with top themes (includes themeId for chaining).

get_theme_changes

Get daily or weekly score movers, stage transitions, and newly emerging themes.

ParameterTypeRequiredDescription
periodstringNo1d (default) / 7d

compare_themes

Compare 2-5 themes side-by-side with scores, stocks, sparklines, and similarity.

ParameterTypeRequiredDescription
theme_idsstring[]YesArray of 2-5 theme UUIDs

get_predictions

Get themes predicted to rise, peak, or cool based on historical analog matching.

ParameterTypeRequiredDescription
phasestringNorising / hot / cooling (default: all)

search_themes

Search themes by keyword, stock name, or stock code.

ParameterTypeRequiredDescription
querystringYese.g. "AI", "반도체", "삼성전자", "005930"

search_stocks

Search stocks by company name or 6-digit code, with related theme preview. Automatically performs stock-to-theme lookup for 6-digit codes.

ParameterTypeRequiredDescription
querystringYese.g. "삼성전자", "SK하이닉스", "005930"

get_stock_themes

Reverse lookup — every theme a stock belongs to, ranked by theme score, each with lifecycle stage and the stock's relevance. Answers "is my stock in a hot theme?"

ParameterTypeRequiredDescription
symbolstringYes6-digit Korean stock code, e.g. "005930" (Samsung), "000660" (SK Hynix)

get_theme_detail

Get detailed analysis: score breakdown (4 components), stage, prediction, stocks, news, comparisons.

ParameterTypeRequiredDescription
theme_idstring (UUID)YesTheme UUID from ranking or search

get_theme_history

Get 30-day score history for trend analysis.

ParameterTypeRequiredDescription
theme_idstring (UUID)YesTheme UUID

get_methodology

Get TLI algorithm documentation — scoring, stages, stabilization, comparison, prediction, data sources, and more.

ParameterTypeRequiredDescription
sectionstringNoscoring / stages / comparison / prediction / all (default: all)

Tip: Use section=scoring to get just the scoring algorithm and save context tokens.

Workflow Prompts

One-click slash commands (in Claude Desktop, Cursor, and other MCP clients) that run complete multi-tool analyses for you — the fastest way to get real value:

PromptArgumentWhat it does
market_briefing—Today's Korean market theme briefing: mood, top themes, movers, takeaways
theme_deep_divethemeFull lifecycle analysis of one theme: score, 30-day trend, stocks, news, outlook
find_investment_themesinterestDiscover themes matching an interest, ranked by momentum and stage
stock_theme_checkstockCheck whether a stock (name or code) sits inside any hot or rising themes

Resources

Attachable read-only context (no tool call needed):

URIDescription
stockmatrix://methodologyHow TLI scores and lifecycle stages are computed — weights and thresholds
stockmatrix://rankingsLive snapshot of today's theme rankings by score, grouped by stage

Scoring Algorithm

TLI scores (0-100) are a weighted sum of 4 components, optimized via Bayesian Optimization:

ComponentWeightSource
Search Interest30.4%Naver DataLab
News Momentum36.6%Naver News
Volatility10.4%Interest time-series
Stock Activity22.6%Naver Finance

Scores are stabilized through Cautious Decay (3-signal majority vote), Bollinger Band Clamp (limits daily change), and Age-adaptive EMA (newer themes react faster).

Lifecycle Stages

Dormant -> Emerging -> Growth -> Peak -> Decline -> Dormant                                          |                                     Reigniting

Stage transitions require 2 consecutive days of the same candidate (hysteresis) and follow Markov transition constraints.

Data Coverage

  • 200+ themes across KOSPI & KOSDAQ
  • Daily updates — scores, news, stock mappings
  • Stock ↔ theme lookup — by company name, 6-digit code, or reverse (stock → all its themes)
  • AI market summary for first-call overview
  • Predictions with historical analog matching
  • Workflow prompts — one-click multi-tool analyses
  • Sources: Naver DataLab, Naver Finance, Naver News

Configuration

VariableDefaultDescription
STOCKMATRIX_API_URLhttps://stockmatrix.co.krOverride API base URL

License

MIT

Links

Source: mcp/README.md at commit 8eb2c73

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.5.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.