# TWStockMCPServer — Taiwan Stock Data MCP Server > TWStockMCPServer is an MCP server for Taiwan market data; verified 85★ and the README cites 143 TWSE OpenAPI tools plus Docker/HTTP modes. ## Install Merge the JSON below into your `.mcp.json`: ## Quick Use ```bash # Docker stdio (README): # {"twstockmcpserver":{"command":"docker","args":["run","-i","--rm","--pull=always","-e","MCP_STDIO=1","ghcr.io/twjackysu/twsemcpserver:latest"]}} # HTTP mode: docker run -d -p 8000:8000 -e PORT=8000 ghcr.io/twjackysu/twsemcpserver:latest # Then set MCP client url to http://localhost:8000/mcp (README). ``` ## Intro TWStockMCPServer is an MCP server for Taiwan market data; verified 85★ and the README cites 143 TWSE OpenAPI tools plus Docker/HTTP modes. **Best for:** Analysts and developers who want market data as MCP tools (not ad-hoc scraping) **Works with:** Any MCP client via streamable HTTP or Docker stdio (per README examples) **Setup time:** 5-15 minutes ### Key facts (verified) - GitHub: 85 stars · 32 forks · pushed 2026-05-13. - License: MIT · owner avatar + repo URL verified via GitHub API. - README-backed entrypoint: `docker run -i --rm ghcr.io/twjackysu/twsemcpserver:latest`. ## Main - Use the Docker stdio config when you want a simple “no-hosting” workflow; use HTTP mode only when you control the network boundary. - Treat tool counts as discoverability: the README lists 143 TWSE OpenAPI tools plus other sources (TPEx/TAIFEX) — start by asking the agent to list available tools for your scenario. - Remember the disclaimer: it’s for reference and not investment advice; use it to analyze data, not to automate trading decisions blindly. ### Source-backed notes - README provides both streamable HTTP usage (remote URL) and Docker stdio configuration examples for MCP clients. - README lists data sources and tool counts, including TWSE OpenAPI (143 tools) plus additional TWSE web APIs, MIS quotes, TPEx, and TAIFEX endpoints. - README includes a disclaimer: for reference only and not investment advice. ### FAQ - **Is Docker required?**: No — README also shows online streamable HTTP usage; Docker is the easiest local path. - **How many tools does it expose?**: README cites 143 TWSE OpenAPI tools plus additional endpoints from other sources. - **Can I use it to trade automatically?**: Don’t — README includes a non-advice disclaimer; use it for analysis and verification. ## Source & Thanks > Source: https://github.com/twjackysu/TWSEMCPServer > License: MIT > GitHub stars: 85 · forks: 32 --- ## Quick Use ```bash # Docker stdio (README): # {"twstockmcpserver":{"command":"docker","args":["run","-i","--rm","--pull=always","-e","MCP_STDIO=1","ghcr.io/twjackysu/twsemcpserver:latest"]}} # HTTP mode: docker run -d -p 8000:8000 -e PORT=8000 ghcr.io/twjackysu/twsemcpserver:latest # Then set MCP client url to http://localhost:8000/mcp (README). ``` ## Intro TWStockMCPServer 为台股市场数据提供 MCP server(TWSE/TPEx/TAIFEX);已验证 85★,README 标注 TWSE OpenAPI 143 个工具,并提供 Docker/HTTP 模式。 **Best for:** 希望把市场数据变成 MCP 工具(而非临时脚本抓取)的分析/开发者 **Works with:** 任意 MCP 客户端:可用 streamable HTTP 或 Docker stdio(README 示例) **Setup time:** 5-15 minutes ### Key facts (verified) - GitHub:85 stars · 32 forks;最近更新 2026-05-13。 - 许可证:MIT;作者头像与仓库链接均已通过 GitHub API 复核。 - README 中可对照的入口命令:`docker run -i --rm ghcr.io/twjackysu/twsemcpserver:latest`。 ## Main - 想省去自建服务就用 Docker stdio;只有在可控网络边界内再开 HTTP 模式。 - 把工具数量当作可发现性:README 提到 TWSE OpenAPI 143 个工具并整合 TPEx/TAIFEX 等来源——先让 agent 列出与你场景相关的工具再深入分析。 - 注意免责声明:仅供参考不构成投资建议;用它做数据分析,不要盲目自动化交易决策。 ### Source-backed notes - README 同时提供 streamable HTTP(远程 URL)与 Docker stdio 的 MCP 客户端配置示例。 - README 列出数据来源与工具数量:包括 TWSE OpenAPI(143 个工具),以及 TWSE Web API、MIS 即时报价、TPEx 与 TAIFEX 等。 - README 写明免责声明:仅供参考,不构成投资建议。 ### FAQ - **必须用 Docker 吗?**:不必。README 也提供线上 streamable HTTP;Docker 是最省事的本地方式。 - **大概有多少工具?**:README 标注 TWSE OpenAPI 143 个工具,并整合其他来源的额外 endpoint。 - **能用来自动交易吗?**:不建议。README 有免责声明;更适合作为分析与核对工具。 ## Source & Thanks > Source: https://github.com/twjackysu/TWSEMCPServer > License: MIT > GitHub stars: 85 · forks: 32 --- Source: https://tokrepo.com/en/workflows/twstockmcpserver-taiwan-stock-data-mcp-server Author: MCP Hub