Related MCP server: matlab-mcp-server-python
通过matlab://documentation/getting-started URI 访问 MATLAB 文档
包含示例和使用说明的入门指南
execute_matlab_code - 执行 MATLAB 代码并获取结果
运行任何 MATLAB 命令或脚本
可选择保存脚本以供将来参考
直接在对话中查看输出
generate_matlab_code - 从自然语言生成 MATLAB 代码
用简单的语言描述你想要实现的目标
获取可执行的 MATLAB 代码作为响应
保存生成的脚本的选项
安装依赖项：
npm install构建服务器：
npm run build对于使用自动重建的开发：
npm run watch您的系统上已安装 MATLAB
Node.js（v14 或更高版本）
要通过Smithery自动为 Claude Desktop 安装 MATLAB MCP 服务器：
npx -y @smithery/cli install @WilliamCloudQi/matlab-mcp-server --client claudenpm install -g matlab-mcp-server或者克隆存储库并自行构建：
git clone https://github.com/username/matlab-mcp-server.git
cd matlab-mcp-server
npm install
npm run build要与 cline 一起使用，请添加服务器配置：
在 MacOS 上： ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"matlab-server": {
"command": "node",
"args": ["/path/to/matlab-server/build/index.js"],
"env": {
"MATLAB_PATH": "/path/to/matlab/executable"
},
"disabled": false,
"autoApprove": []
}
}
}将/path/to/matlab/executable替换为您的 MATLAB 可执行文件的路径：
Windows：通常为C:\\Program Files\\MATLAB\\R2023b\\bin\\matlab.exe
macOS：通常为/Applications/MATLAB_R2023b.app/bin/matlab
Linux：通常为/usr/local/MATLAB/R2023b/bin/matlab
由于 MCP 服务器通过 stdio 进行通信，调试起来可能比较困难。我们推荐使用MCP Inspector ，它以包脚本的形式提供：
npm run inspector检查器将提供一个 URL 来访问浏览器中的调试工具。
Execute MATLAB code and return the results
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | MATLAB code to execute | |
| saveScript | No | Whether to save the MATLAB script for future reference | |
| scriptPath | No | Custom path to save the MATLAB script (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral disclosure burden. It states the basic action and result but does not disclose execution side effects, persistence between calls, result format, or how saveScript and scriptPath affect behavior. This is thin for an arbitrary code-execution tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one compact sentence with no filler and the primary action is front-loaded. It is concise, though arguably too terse given the missing behavioral context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one required parameter and fully documented optional parameters, the schema plus description are mostly usable. However, with no output schema and no annotations, the vague phrase 'return the results' leaves the return format undefined, and no execution-environment context is given.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter is already documented in the schema. The description adds no additional meaning for 'code', 'saveScript', or 'scriptPath', so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Execute'), identifies the target ('MATLAB code'), and notes the outcome ('return the results'). It is clear on its face but does not explicitly distinguish this tool from its sibling generate_matlab_code, so it stops short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to choose execute_matlab_code over generate_matlab_code, and there are no exclusions or prerequisites. The intended use must be inferred from the tool name and basic semantics rather than from explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate MATLAB code from a natural language description
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | Natural language description of what the code should do | |
| saveScript | No | Whether to save the generated MATLAB script | |
| scriptPath | No | Custom path to save the MATLAB script (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says code will be generated; it does not explain whether code is returned, saved, or how the optional saveScript/scriptPath parameters affect behavior. It also does not state that this tool does not execute the generated MATLAB code.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. It communicates the primary function efficiently, and every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description leaves important operational details unstated: how the generated code is returned to the agent, what the default saving behavior is, and how it relates to execute_matlab_code. These gaps could cause incorrect invocation or misunderstanding of the tool's response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers all three parameters with descriptions, so the baseline is 3. The description's 'from a natural language description' slightly reinforces the central 'description' parameter, but it adds no meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Generate') and resource ('MATLAB code'), making the core purpose clear. It does not explicitly contrast itself against the sibling execute_matlab_code, so the differentiation is only implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance about when to choose this tool over execute_matlab_code, and no mention of prerequisites or intended workflow. The agent must infer that 'generate' means code creation rather than execution, but the description offers no explicit selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0execute_matlab_codegenerate_matlab_codeScored across 2 tools
The two tools have clearly distinct purposes: one executes existing MATLAB code, while the other generates new code from natural language. There is no overlap or ambiguity between these functions, making it easy for an agent to select the correct tool based on the task.
Both tool names follow a consistent verb_noun pattern (execute_matlab_code and generate_matlab_code), using the same verb style and snake_case formatting. This predictability aids in understanding and usage without any deviations.
With only two tools, the server feels thin for a MATLAB domain, which typically involves more operations like plotting, data analysis, or file management. While the tools cover core execution and generation, the scope is limited and may not support complex agent workflows effectively.
The tool set is severely incomplete for a MATLAB server, lacking essential operations such as loading/saving data, creating plots, debugging code, or managing variables. Agents will face significant gaps when trying to perform common MATLAB tasks beyond basic code execution and generation.
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
