Stock Analyzer MCP

An MCP server with deep Taiwan stock coverage(TWSE / TPEx + three major institutional flows + chip data + monthly revenue). 95 tools across 15 categories + 6 resources.Local-first— runs in-process inside the Electron app, no API costs, no cloud dependency.

Current version: MCP server1.3.0· Stock Analyzer app0.48.0-beta· Updated 2026-06-30

This repo contains theMCP shim source(mcp-server.js + lib/ai-tools + Dockerfile). The shim is athin HTTP-to-stdio bridge— when an MCP client invokes a tool, the shim proxies the call tohttp://localhost:3000/api/, where theStock Analyzer desktop app's embedded Express backenddoes the actual work (DB query, computation, analysis).

Image is ~258 MB (node:20-alpine + 2 npm deps). The build skipsbetter-sqlite3, Electron, and other backend-only dependencies because the shim itself never imports them — all data calls go via HTTP to the locally-running Stock Analyzer app's/api/endpoints.

- annotations.readOnlyHint— whether the tool modifies state (clients auto-confirm before destructive ops)
- annotations.destructiveHint—delete_/cancel_flagged true
- annotations.idempotentHint—upsert_/update_flagged true
- _meta.tw.stockanalyzer/estimated_cost_usd— worst-case LLM cost (most tools $0; deep-dive ~$0.16)

6 resources (Claude Desktop@-mentionable)

Inject context into your conversation without burning tool calls:

SetSAA_MCP_PROFILEenv var to gate which tools are visible to the LLM client:

Resources stay available in both profiles (they're read-only by definition).

For non-Taiwan readers: Taiwan stock market has its own data ecosystem (TWSE, TPEx OpenAPI, three major institutional investors, monthly revenue reporting) that's nearly absent from English-speaking financial data platforms. If you want an AI agent that can answer "How are TSMC's institutional investors trading lately?" or "Find me TW small-caps with >30% YoY revenue growth", Stock Analyzer MCP is built for exactly this — deterministic TW chip/institutional/revenue tools that English-focused MCP servers generally lack.

Edit~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "stock-analyzer": { "command": "/Applications/Stock Analyzer.app/Contents/Resources/app.asar.unpacked/bin/saa-mcp", "env": { "PORT": "3000" } } } }

Why the wrapper?Runningnode mcp-server.jsdirectly hits abetter-sqlite3ABI mismatch (the binding is compiled for Electron's Node, not the system's). Thebin/saa-mcpwrapper auto-finds the SAA Electron runtime and runs the MCP server withELECTRON_RUN_AS_NODE=1. Older configs that point tonodewill need updating.

3. (Optional) Restrict to read-only mode

If the LLM client isn't fully trusted (shared Claude project, third-party agent), add:

"env": { "PORT": "3000", "SAA_MCP_PROFILE": "safe_readonly" }

This blocks 15 write tools (add_trade,delete_trade,upsert_thesis,set_price_alert, etc.) but keeps all read tools + all 6 resources.

4. Fully restart Claude Desktop (cmd+Qthen reopen)

"List all SAA stock-analyzer tools"

"Analyze 2330 — institutional flow last month + 3-month momentum + radar score + give me a buy/sell view"

"@saa://portfolio — what's my biggest concentration risk?"

"Compare 2330, 2454, and 3008 as candidates. Include their theses if they exist."

Claude will orchestrate multiple tool calls (or@-mentions for resources) and synthesize a research report.

🎭research_stock_deep_dive— Premium tier

5 specialized AI agents debate in parallel:

- 🐂 Bull (only sees evidence supporting an upside thesis)
- 🐻 Bear (only sees evidence supporting a downside thesis)
- 📰 Sentiment (news + social signals)
- 🛡️ Risk (volatility, drawdown history, regime context)
- 🎯 Synthesizer (sees all four; produces a 6-level action:strong_buy→avoid)

Each agent uses a distinct subset of the 95 tools. Output includes per-agent reasoning + final action + confidence score. ~$0.16/call LLM cost (Anthropic Sonnet / OpenAI).

Pre-market or post-market portfolio briefing. Aggregates current holdings, unrealized P&L, sector exposure, relevant macro / institutional flow into an actionable summary.

- mode='get'→ reads the latest cached briefing (free, instant)
- mode='generate'→ runs a fresh one (~10-20s, ~$0.04/call LLM cost)

🔍compare_investment_candidates— Lite, cost $0

Side-by-side deep analysis of 2-5 candidate stocks. Parallel fan-out ofget_full_stock_analysis(fundamentals + technical + chip + institutional + levels) per candidate, plus existing thesis status.Deterministic— the agent sees raw evidence rather than an LLM-synthesized opinion, which empirically produces better reasoning.

Past-N-days reflection. Aggregatesanalyze_trade_performance(FIFO P&L, win rate, hold time) +get_trade_journal(recent trades) +get_portfolio_signals(current state). Auto-detects observable patterns:

- low_win_rate(< 40%) → systematic selection or timing problem
- over_trading(avg hold < 5 days) → fees eating returns
- lopsided_pnl(avg loss > avg win) → poor stop-loss discipline

Hands the agent objective indicators to write narrative review against.

- Local-first: All data lives in~/.twse-analyzer/stock_history.db(SQLite, single file). MCP server runs in-process inside the Electron app via stdio transport.
- BYOK LLM: SAA itself has an AI Hub that consumes the same 95 tools. Bring your own keys (Claude / GPT / Gemini / Ollama). The MCP server itself isn't tied to any LLM — it just exposes deterministic data + a few LLM-backed aggregators.
- Transparent methodology: 16 bilingual methodology pages (zh-TW + en) explain every analytical tool's formula, data source, and limitations. Available at/methodology.htmlinside the app.
- No active trading signals: Research output only — not order execution. Regulatory + product positioning decision.
- Cost honesty: Every tool surfaces its worst-case LLM cost upfront via_meta.tw.stockanalyzer/estimated_cost_usd. No hidden cloud-API spend.

The MCP server uses two version numbers:

- patch— additive (new tool, new resource)
- minor— new required param, new enum restriction,readOnlyHintchange
- major— rename, removal, required-keys change

Current: server1.2.0, schema1.2.0. Changelog insidemcp-server.jsheader.

Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.

Portfolio & trading-strategy stress diagnostics for AI agents: multi-asset stress with hedge-break detection, a daily preregistered regime outlook and deflated-Sharpe backtest-integrity checks. Remote streamable HTTP, free tier, no auth.

Give any AI agent the power to run a serious Monte Carlo forecast for a stock or ETF - in one tool call.

Market intelligence your AI agent can call

Financial intelligence for AI agents: an agent-readable investment loop for market regime, portfolio context, decision framing, and thesis review.

Estimates departmental value-leak (wasted spend/time) from headcount and labor cost data for Claude, Cursor, and other MCP agents.

An MCP server which can be integrated in your Claude system to guide you better calculate the Personal Finance calculations in Claude ecosystem

Measured market statistics for AI agents — day-type probabilities, volume-wave events with measured win rates, options max pain and dealer gamma; remote MCP at https://api.quantdata.uk/mcp, no key needed to try.

Official Santiment MCP server — behavior analytics for crypto. Query on-chain metrics, social sentiment, trending narratives, and analyst insights directly from Claude, ChatGPT, and other AI tools.