mcp-llm
MCP 法学硕士
使用 LlamaIndexTS 库提供对 LLM 的访问的 MCP 服务器。

特征
该 MCP 服务器提供以下工具:
generate_code:根据描述生成代码generate_code_to_file:生成代码并将其直接写入特定行号的文件中generate_documentation:生成代码文档ask_question:向 LLM 提问


Related MCP server: Globalping
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 LLM 服务器:
npx -y @smithery/cli install @sammcj/mcp-llm --client claude从源手动安装
克隆存储库
安装依赖项:
npm install构建项目:
npm run build更新您的 MCP 配置
使用示例脚本
该存储库包含一个示例脚本,演示如何以编程方式使用 MCP 服务器:
node examples/use-mcp-server.js该脚本启动 MCP 服务器并使用 curl 命令向其发送请求。
示例
生成代码
{
"description": "Create a function that calculates the factorial of a number",
"language": "JavaScript"
}生成代码到文件
{
"description": "Create a function that calculates the factorial of a number",
"language": "JavaScript",
"filePath": "/path/to/factorial.js",
"lineNumber": 10,
"replaceLines": 0
}generate_code_to_file工具支持相对路径和绝对路径。如果提供了相对路径,则会根据 MCP 服务器的当前工作目录进行解析。
生成文档
{
"code": "function factorial(n) {\n if (n <= 1) return 1;\n return n * factorial(n - 1);\n}",
"language": "JavaScript",
"format": "JSDoc"
}提问
{
"question": "What is the difference between var, let, and const in JavaScript?",
"context": "I'm a beginner learning JavaScript and confused about variable declarations."
}执照
Available Tools
4 toolsask_questionC
Ask a question to the LLM
Inputs: question (required), context.
generate_codeC
Generate code based on a description
Inputs: description (required), language, additionalContext.
generate_code_to_fileB
Generate code and write it directly to a file at a specific line number
Inputs: description (required), filePath (required), lineNumber (required), language, +2 more.
generate_documentationC
Generate documentation for code
Inputs: code (required), language, format.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
The tools have overlapping purposes that could cause confusion. 'generate_code' and 'generate_code_to_file' both generate code, with the latter adding file writing functionality, which might lead to misselection when file output isn't needed. However, 'ask_question' and 'generate_documentation' are more distinct in their purposes, helping to mitigate some ambiguity.
The naming follows a consistent verb_noun pattern throughout, such as 'ask_question' and 'generate_documentation'. There is a minor deviation with 'generate_code_to_file', which includes a prepositional phrase, but overall the pattern is clear and readable, maintaining good consistency.
With 4 tools, the count is slightly low but reasonable for an LLM-focused server. It covers core functionalities like questioning, code generation, and documentation, though it might feel thin if more advanced features are expected. The scope is well-defined, so the number is appropriate for basic operations.
There are notable gaps in the tool surface for an LLM domain. While it covers code generation and documentation, it lacks tools for editing, refactoring, or analyzing existing code, and there's no way to manage conversations or context. This could lead to agent failures in more complex workflows, but core tasks are addressed.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Related MCP Servers
- MIT

Globalpingofficial
FlicenseNot gradedqualityCmaintenanceRemote MCP server that gives LLMs access to run network commands66-- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs4 npm1MIT
- AlicenseAqualityAmaintenanceFilesystem MCP server for AI assistants. Search, read, edit, and manage local files in directories you choose.6141,447 npm34MIT