Skip to main content
Glama
dse-mcp

dse-mcp

by ofsazib

dse-mcp

PyPI Python CI License: MIT MCP

A production-grade Model Context Protocol (MCP) server for the Dhaka Stock Exchange (DSE) — live quotes, price history, fundamentals, order-book depth, news, technical indicators, screening — plus a bundled dse-analysis skill that teaches your agent a disciplined buy/sell workflow on top of those tools.

Data is scraped from dsebd.org (DSE's official site) with all of its production quirks handled: incomplete TLS chains, -- placeholders, comma-grouped numbers, invisible layout tables, market-hours-aware caching, and a mirror-domain fallback. Informational only — not investment advice. Not affiliated with DSE.

Install

Requires Python 3.12+ (or just uv/pipx, which manage Python for you).

# Register with Claude Code (recommended)
claude mcp add dse -s user -- uvx dse-mcp

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "dse": { "command": "uvx", "args": ["dse-mcp"] }
  }
}

Cursor (~/.cursor/mcp.json): same JSON shape as Claude Desktop.

pipx:

pipx install dse-mcp
# then register with the command "dse-mcp"

Docker:

docker run -i --rm ghcr.io/ofsazib/dse-mcp

Related MCP server: Stock SDK MCP Server

The dse-analysis skill

The repo ships an agent skill that turns these tools into a repeatable buy/sell analysis workflow (market context → fundamentals → technicals → news → verdict with confidence + risks):

# from a git clone of this repo
./scripts/install_skill.sh              # installs to ~/.claude, ~/.agents, ~/.zcode
./scripts/install_skill.sh --dir ~/x    # add a custom skills directory
./scripts/install_skill.sh --uninstall  # remove from all configured directories

Or copy skills/dse-analysis/ into your client's skills directory manually.

Removing everything

claude mcp remove dse                    # unregister the MCP server (add -s user if needed)
./scripts/install_skill.sh --uninstall   # remove the skill from all skill directories
uv cache clean dse-mcp                   # drop uvx's cached build of the package

Tools (16)

Every response carries market_status (live/closed), data_freshness (live/snapshot/stale), and data_as_of — so closed-market data is never mistaken for live prices.

Market

Tool

Description

market_status

Live/closed, session hours, Dhaka time, next session

market_summary

DSEX/DS30/DSES + changes, totals for the latest session

get_index_history(days)

Daily index history (rolling one-year archive)

top_movers(category)

gainers | losers | most_active | turnover

sector_performance

Advancing/declining + avg change per sector

Stock

Tool

Description

search_symbols(query)

Fuzzy search over 636 bundled instruments (22 sectors)

get_quote(symbol)

LTP, day range, close, change, trades, value, volume

get_price_history(symbol, start, end, days)

Day-end OHLCV, oldest-first

get_company_profile(symbol)

Capital structure, listing year, 52w range, EPS block

get_fundamentals(symbol)

Analysis-ready: EPS, P/E, dividends, reserves, 52w

get_market_depth(symbol)

Live bid/ask levels + session stats

get_news(symbol, days, limit)

Company or market-wide news/disclosures

get_pe_ratios()

P/E table (interim/audited/trailing) for all instruments

Analysis & screening

Tool

Description

compute_indicators(symbol, ...)

SMA50/200, RSI(14), MACD, Bollinger

technical_summary(symbol)

Trend, support/resistance, outlook + reasons

screen_stocks(sector, pe_max, price_range, volume_min)

Filter the live board

Trading-hours aware caching

  • Market live (Sun–Thu 10:00–14:50 Asia/Dhaka): data cached 30s (depth is always fetched fresh).

  • Market closed: the last session's snapshot is cached ~1h and persisted to ~/.cache/dse-mcp/, so a restart still serves the last session (labeled snapshot).

  • DSE unreachable: the persisted snapshot is served labeled stale.

Configuration (optional)

All via environment variables with the DSE_MCP_ prefix — see .env.example. Useful ones:

Variable

Default

Purpose

DSE_MCP_RATE_LIMIT

5.0

Outbound requests/second (token bucket)

DSE_MCP_CACHE_TTL_OPEN

30

Seconds, while the market is live

DSE_MCP_CACHE_DIR

~/.cache/dse-mcp

Snapshot persistence

DSE_MCP_LOG_LEVEL

WARNING

Logs go to stderr (never stdout — MCP)

Troubleshooting

  • [SSL: CERTIFICATE_VERIFY_FAILED] — dsebd.org serves an incomplete TLS chain. dse-mcp uses the OS trust store (truststore), which handles it; do not replace it with verify=False.

  • Empty depth / quotes look frozen — the market is closed (or a holiday). Check market_status and the response's data_as_of.

  • DGEN: null — the DGEN index is retired from DSE's live pages; null is the honest value.

Development

git clone https://github.com/ofsazib/dse-mcp && cd dse-mcp
uv sync                                   # Python 3.12 via uv
uv run pytest                             # 44 offline tests (recorded fixtures)
uv run ruff check .
uv run dse-mcp                            # run the server locally
npx @modelcontextprotocol/inspector uv run dse-mcp   # visual debugging

Re-record fixtures when dsebd.org markup changes: uv run python scripts/record_fixtures.py. Rebuild the instrument bundle: uv run python scripts/build_instruments.py. See AGENTS.md for architecture and CONTRIBUTING.md to contribute.

  • Data source: dsebd.org (Dhaka Stock Exchange). This project is an independent, unaffiliated open-source client; data remains the property of DSE.

  • Nothing here is investment advice. DSE securities can be illiquid and subject to circuit breakers; verify everything against primary sources before acting.

License

MIT © Omar Faruk Sazib

Available Tools

16 tools
compute_indicatorsCompute IndicatorsA

Compute technical indicators for a symbol over the last year of day-end candles. Values are null when history is too short (e.g. recent IPOs).

Inputs: symbol (required), macd, rsi_14, sma_50, +2 more. Returns: object

get_company_profileGet Company ProfileB

Company profile from displayCompany: capital structure, listing year, market lot, 52-week range, latest dividend status, EPS block.

Inputs: symbol (required). Returns: object

get_fundamentalsGet FundamentalsB

Analysis-ready fundamentals: EPS, P/E (interim/audited/trailing), dividend yield + latest dividend, reserves, market cap, 52-week range.

Inputs: symbol (required). Returns: object

get_index_historyGet Index HistoryA

Daily index history (DSEX, DS30, totals) for the last N days (max ~365; DSE keeps a rolling one-year archive).

Inputs: days. Returns: object

get_market_depthGet Market DepthB

Live order book: best bid/ask levels with volumes, plus session price statistics. Empty sides are normal outside trading hours.

Inputs: symbol (required). Returns: object

get_newsGet NewsA

Company or market-wide news/disclosures. Omit symbol for market-wide (inst=All); returns newest items first with titles, bodies, post dates.

Inputs: days, limit, symbol. Returns: object

get_pe_ratiosGet Pe RatiosB

P/E table for all instruments (interim basic/diluted, audited, trailing).

Inputs: no named parameters. Returns: object

get_price_historyGet Price HistoryA

Day-end OHLCV candles, oldest-first. Give ISO start/end, or just days (default 90; DSE keeps a rolling one-year archive).

Inputs: symbol (required), end, days, start. Returns: object

get_quoteGet QuoteA

Latest quote for one instrument: LTP, day range, close, YCP, change, trades, value, volume. Untraded instruments carry traded=false.

Inputs: symbol (required). Returns: object

market_statusMarket StatusA

Current DSE market state: live or closed, session hours, Dhaka local time.

Inputs: no named parameters. Returns: object

market_summaryMarket SummaryA

Latest market snapshot: DSEX/DS30 indices + changes, session totals, and DSES from the 30-day market information table.

Inputs: no named parameters. Returns: object

screen_stocksScreen StocksA

Filter the live board: sector (case-insensitive substring), max P/E (interim basic, falls back to trailing), price range, minimum volume. Untraded instruments are excluded. Sorted by traded value (turnover).

Inputs: limit, pe_max, sector, price_max, +2 more. Returns: object

search_symbolsSearch SymbolsA

Find DSE instruments by trading code or company name (case-insensitive).

Inputs: query (required), limit. Returns: object

sector_performanceSector PerformanceA

Aggregate live-quote performance per sector: advancing/declining counts and average change percent, sorted best-to-worst.

Inputs: no named parameters. Returns: object

technical_summaryTechnical SummaryA

Rule-based technical read: trend (SMA50/200 cross), RSI zone, MACD direction, Bollinger position, support/resistance, volume context, and a plain-language outlook with reasons. Informational only.

Inputs: symbol (required). Returns: object

top_moversTop MoversA

Top movers by category: gainers | losers | most_active | turnover.

Gain/loss lists reflect the +-10% circuit breaker; turnover leaders are computed from live quotes (untraded instruments excluded).

Inputs: category. Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 16 tools

    Disambiguation4/5

    Each tool targets a distinct data aspect (quotes, history, fundamentals, news, technicals), so most boundaries are clear. However, get_company_profile, get_fundamentals, and get_pe_ratios share overlapping metrics like EPS and P/E, which could cause confusion if an agent relies on descriptions alone.

    Naming Consistency4/5

    The naming pattern is mostly get_ for retrievals and noun phrases for snapshots (market_summary, top_movers), which is readable and predictable. Minor deviations like search_symbols versus get_index_history and compute_indicators versus technical_summary keep it from being fully uniform.

    Tool Count4/5

    With 16 tools, the server is on the upper end but still well-scoped for a stock exchange data platform. Each tool earns its place by covering a meaningful query type—pricing, fundamentals, news, technicals—without unnecessary fragmentation or duplication.

    Completeness4/5

    The surface covers the core domain well: market state, indices, quotes, history, fundamentals, news, screening, and technical analysis. Minor omissions like a direct list-all-instruments endpoint or corporate actions beyond dividends are workable through search_symbols and screen_stocks, so no severe dead ends exist.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      D
      maintenance
      Enables querying real-time and historical financial market data for stocks, options, forex, and crypto, including quotes, trades, technical indicators, and reference data through a set of MCP tools.
      71
      3
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to access real-time and historical market data for A-shares, Hong Kong, US stocks, funds, futures, and options, calculate technical indicators, screen stocks, and perform composite market analysis through MCP tools, prompts, skills, and resources.
      153 npm
      ISC
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to access real-time and historical market data across A-share, Hong Kong, and US stocks, funds, futures, and options, plus technical indicators, sector data, screeners, and composite analysis tools. It also provides MCP prompts, resources, and ready-to-use skills for stock analysis, market overviews, comparisons, and monitoring.
      153 npm
      ISC
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to retrieve real-time and historical market data across A-shares, Hong Kong, US stocks, funds, futures, and options, calculate technical indicators, and perform stock screening, comparison, and market or sector analysis through MCP tools, prompts, resources, and skills.
      153 npm
      ISC