{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_drjp7cbuzx2y","handle":"baltamatica-mcp","url":"https://wellknown.network/agents/baltamatica-mcp","links":{"self":"https://wellknown.network/agents/baltamatica-mcp/record.json","html":"https://wellknown.network/agents/baltamatica-mcp","markdown":"https://wellknown.network/agents/baltamatica-mcp/record.md","api":"https://wellknown.network/api/v1/agents/baltamatica-mcp","status":"https://wellknown.network/api/v1/agents/baltamatica-mcp/status","claim":"https://wellknown.network/agents/baltamatica-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/baltamatica-mcp/claim.json","badge":"https://wellknown.network/agents/baltamatica-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/baltamatica-mcp/history","tools":"https://wellknown.network/api/v1/agents/baltamatica-mcp/tools"},"ard":{"identifier":"urn:air::server:baltamatica-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"baltamatica-mcp","summary":"MCP server for Baltamatica (北太天元) scientific computing engine","description":"# baltamatica.mcp\n\n[![PyPI](https://img.shields.io/pypi/v/baltamatica-mcp.svg)](https://pypi.org/project/baltamatica-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![MCP Protocol](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.io)\n[![Baltamatica](https://img.shields.io/badge/Baltamatica-2025-orange.svg)](https://www.baltamatica.com)\n\n> 🔗 让 AI 代理（Claude Code / Cursor / Codex）直接驱动国产科学计算软件 **北太天元（Baltamatica）** 进行交互式数值计算。\n\n---\n\n## 📖 项目简介\n\n**baltamatica.mcp** 是一个基于 [Model Context Protocol (MCP)](https://modelcontextprotocol.io) 的开源服务，为大语言模型提供与北太天元科学计算内核之间的双向通信桥梁。\n\n通过本项目，AI 代理可以：\n\n- 🧮 **执行代码**：直接在北太天元中运行 `.m` 脚本或单行表达式，并取回控制台输出\n- 📊 **读取变量**：获取工作区中矩阵、向量、结构体、元胞等变量的值（BEX 后端二进制全保真）\n- ✍️ **写入变量**：把标量/向量/矩阵注入工作区（`set_variable`）\n- 🔍 **查询状态**：列出当前工作区中所有变量的名称、类型和维度\n- 📂 **管理脚本**：运行本地 `.m` 脚本文件\n- 🧹 **清空工作区**：重置计算环境\n\n**当前状态**：两套后端均可用。\n\n- **CLI 后端**：通过北太天元命令行入口执行代码，用 `.mat` 状态文件在多次 MCP 调用之间保持工作区变量。支持全部 6 个工具。\n- **BEX 后端**：在北太天元 GUI 进程内运行的 C 桥接（JSON-over-TCP），支持 `execute_code`、`run_script`、`list_variables`、`get_variable`、`set_variable`、`clear_workspace`：\n  - `get_variable` 对数值/逻辑数组（实数**和复数**、任意大小）走 base64 二进制全保真回传，对字符/字符串/结构体/元胞走结构化 JSON；\n  - `set_variable` 用 `bxAddVariable` 把标量/向量/矩阵注入工作区；\n  - `execute_code` / `run_script` 用 `evalc` 捕获控制台输出并解析 `BALTAMATICA_ARTIFACT=` 文件产物；\n  - 桥接生命周期健壮（可靠 `stop`、Ctrl-C 恢复、`background` 模式），并可触发 GUI Figure 弹窗（但北太天元本身无图形导出函数，见下）。\n\n---\n\n## 🏗️ 系统架构\n\n项目提供两套后端。**CLI 后端**通过北太天元命令行入口执行代码，用 `.mat` 状态文件保持工作区变量，无需编译，适合快速上手。**BEX 后端**是一个在北太天元 GUI 进程内运行的 C 桥接，走 **JSON-over-TCP**，提供进程内低延迟长连接、二进制变量传输和变量注入。两者暴露相同的 MCP 工具集。\n\n```\n┌──────────────────────────────────────────────────────────┐\n│            AI Agent (Claude Code / Cursor / Codex)         │\n└─────────────────────────┬────────────────────────────────┘\n                          │ MCP Protocol (stdio)\n                          ▼\n┌──────────────────────────────────────────────────────────┐\n│               Python MCP Server (balta…","publisher":{"name":"wzlwww","url":null},"homepage":"https://github.com/wzlwww/baltamatica.mcp","repository":"https://github.com/wzlwww/baltamatica.mcp","version":"0.2.2","license":"MIT","protocols":["mcp"],"tags":["ai-agent","baltamatica","mcp","scientific-computing"],"pricing":null,"endpoints":[{"url":"pypi:baltamatica-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"derived"}],"categories":["research"],"language":"fr"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"baltamatica-mcp","registry":"pypi","observedAt":"2026-11-02T22:24:51.769Z","publishedAt":"2026-07-02T07:32:24.384490Z","latestVersion":"0.2.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"baltamatica-mcp","url":"https://pypi.org/project/baltamatica-mcp/","firstSeenAt":"2026-09-09T10:26:31.886Z","fetchedAt":"2026-11-02T22:23:43.932Z","normalizedAt":"2026-11-02T22:23:43.932Z"}]},"firstSeenAt":"2026-09-09T10:26:31.886Z","updatedAt":"2026-11-02T22:24:51.769Z"}