jacobian
English · 简体中文
Jacobian 是一个 MCP 服务器,为 AI 智能体提供可搜索的类型化数学操作词汇表。math.find 用于发现操作,math.run 则执行一个有界数学契约并返回类型化结果。同一数学库也可通过 CLI 和原生 Python API 使用。
每个操作都建立了一个稳定、可复用的数学后置条件,而非规定工作流或证明策略。结果在声明处精确,并明确标注近似、不完备或不确定性。
Jacobian 的假设是:数学推理受益于一个由语义上有界、范围明确的操作组成的可执行词汇表。 与其暴露大型领域求解器或预组合工作流,Jacobian 提供的是数学原语,智能体可以搜索这些原语并组合出超出任何单个操作设计目标的解决方案。该库提供可信的数学步骤;推理模型决定执行哪些步骤、如何组合其结果以及何时停止。保持操作的语义狭窄且领域专属,从而保留了搜索空间,而不是将某种证明策略或工作流固化到工具本身中。
参见可执行数学词汇表,了解语义原子性的含义以及操作词汇表如何扩展。
快速开始
在不全局安装 Jacobian 的情况下运行标准 Python MCP 命令:
uvx --from jacobian jacobian-mcp当 MCP 主机需要 npm 命令时,npm 包是该命令的确定性载体:
npx jacobian mcp对于持久化安装:
python -m pip install jacobian
jacobian-mcp该包包含 Jacobian 精确维护的 Python 后端技术栈:SymPy、NetworkX、Z3 和 Python-FLINT。因此,常规的 Python 或 npm 安装会暴露相同的、基于 Python 的操作组合。经过测试的二进制安装契约是 CPython 3.12 或 3.13,运行于 glibc Linux x86-64 平台;发布门禁会安装构建好的 wheel 并在两个 Python 版本上启动 Jacobian。其他系统可能具有兼容的上游 wheel,但不属于已测试的发布契约。特别是,Alpine/musl 无法从 PyPI 安装完整的必需技术栈。
Python 发行版包含数学内核、CLI 和 MCP 服务器。npm 包将其精确的包版本确定性地映射到相应的 uvx 调用。
Related MCP server: math-logic-mcp
计算一个有界结果
一个普通操作首先返回数学结果。例如,matrix.determinant.compute 接受一个精确有理矩阵并返回其行列式。调用者通过传递类型化值来组合结果,以进行后续操作。
可用的数学内容
内置操作组合涵盖以下领域:
多项式映射与多项式代数;
精确线性代数;
图、路径、着色与同构;
有界 SAT 与 SMT 求解;
有限代数、概率、几何与拓扑;
Lean 源码精化。
SAT 与 SMT 操作直接使用维护的 Z3 Python 绑定。可选的 lean.check 操作在固定的 Lean 服务环境中运行一个有界源码片段,使用请求作用域的临时目录,并返回类型化诊断信息。使用 math.find 搜索操作、浏览不熟悉的领域,并在调用 math.run 之前检查某个操作。
状态
Jacobian 0.12.0 为预稳定版本。其已发布的包和操作契约描述了受支持的接口;实验性操作契约可能在版本之间发生变化。
文档
文档首页:教程、操作指南、参考和解释
架构:运行时结构与信任边界
产品模型:操作契约、所有权与项目边界
工具参考:MCP 资源与调用契约
后端要求: 受维护的 Python 后端与可选的 Lean
远程部署:HTTP 部署与认证
贡献
Jacobian 使用 Python 3.12、uv 和一个精简的 Makefile:
make setup
make test-math
make check在修改代码之前,请阅读 CONTRIBUTING.md。其中记录了聚焦的测试命令、验证规则、文档放置位置以及拉取请求的期望。
许可证
Available Tools
2 toolsmath.findSearch installed Jacobian math toolsARead-onlyIdempotent
Find or inspect public Jacobian MCP operations.
Forms:
query: describe one local mathematical need in ordinary language.namespace,limit,cursor, andsearch_modeare optional search controls. Preserve established mathematical names from the task, the supplied objects and constraints, the requested computation or decision, the full scalar, batch, or exhaustive scope, and whether the requested result is a value, witness, certificate, obstruction, profile, or complete enumeration. Do not replace a supplied named property only with its expanded definition, translate the need into catalog tags, or submit the surrounding proof goal.operation_id: pass one exact operation ID to receive its authoritative input and output schemas, operator-authored examples, and current optional backend availability. Matches expose staticruntime_requirements; inspection checks these runtimes in the server environment.
For matching, use namespace only when the primary operation-ID namespace is already
known with high confidence. Matching returns 10 candidates by default; request up to
20 when a wider first page is useful. Follow next_cursor with the same query, namespace, and search_mode
to continue; the limit may change. Ordered matches are deterministic retrieval candidates, not
applicability claims; inspect a promising operation before math.run. Read
operation://catalog only when the complete bulk catalog is genuinely needed.
An unknown operation ID returns kind: "error" with error.code: "UNKNOWN_OPERATION";
inspect kind even when MCP isError is false. Search with query to find an
installed operation, then inspect its exact ID. Zero matches is a successful search.
Examples:
{"query":"exact determinant of a rational matrix","namespace":"matrix","limit":3}{"operation_id":"polynomial.compute.gcd"}
Inputs: limit, query, cursor, namespace, +2 more. Returns: Closed discriminated output returned directly through MCP SDK 2.0.
math.runRun one installed Jacobian math toolARead-only
Run one installed math tool by ID with its typed payload. A successful call returns
the operation-owned canonical mathematical value in output; a later inspected
operation may accept that complete value unchanged. Read its fields to determine what
the calculation established. MCP reports malformed payloads, unknown IDs, and host
failures as tool errors, not as mathematical results. If the payload shape is unknown,
inspect the exact operation with math.find. When it publishes an examples item, copy
and adapt that item's input object as the payload; otherwise, form the payload from
the input schema and its field descriptions. Do not call math.run with an empty
payload merely to discover required fields; inspection is authoritative.
Timeout, incomplete search, and missing witnesses appear only in the concrete domain result that owns them; none is a mathematical conclusion by itself.
Examples:
{"operation_id":"integer.compute.extended_gcd","payload":{"left":"84","right":"30"}}
Inputs: payload (required), operation_id (required). Returns: The final transport envelope around one direct mathematical result.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
math.find is clearly for discovery and inspection of operations, while math.run is clearly for executing a chosen operation. Their purposes do not overlap and the descriptions consistently direct users to inspect before running.
Both tools follow the same math.<verb> pattern with lowercase snake_case verbs. The naming is predictable and consistent across the set.
Two tools are sufficient for a dispatcher-style math catalog: one to find/inspect operations and one to run them. It is slightly below the typical 3-15 range, but the minimal surface is justified by the server's purpose.
The set covers the core lifecycle: search, inspect schemas/examples, and execute an operation by ID. Minor gaps exist for batch execution, composition, or direct catalog listing, but these are workable through repeated calls.
Maintenance
Related MCP Connectors
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
Math MCP server for primality, factorization, Java templates, and integer multiplication.
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
Deterministic physics runtime with a proof on every answer: 61 models, open and keyless over MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for step-by-step mathematical reasoning and planning, enabling AI agents to execute calculations and perform GUI actions like opening PowerPoint.1Apache 2.0
- AlicenseAqualityDmaintenanceMCP server that gives small LLMs verified symbolic-math & logic tools.62Apache 2.0
- AlicenseBqualityBmaintenanceMCP server for symbolic computation that enables AI agents to perform step-by-step derivations, transform formulas, and verify results with full provenance, combining natural language with formal mathematical operations.4113Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server for semantic search over 9.27 million mathematical statements from sources like arXiv and Stacks Project, offering 5 tools for filtered search, citation weighting, and dependency graph traversal.MIT