LDIMS MCP

# 编译 npm run build # MCP客户端会自动调用 node dist/index.js # Token通过MCP配置传递，不需要.env文件中的LDIMS_AUTH_TOKEN

# 确保.env文件中配置了LDIMS_AUTH_TOKEN npm run http # 或直接运行 node dist/http-server.js

- MCP模式：使用MCP客户端配置中的Token
- HTTP模式：使用.env文件中的LDIMS_AUTH_TOKEN
- 两种模式独立配置，互不干扰

node scripts/update-env-token.js <new_token>

- ✅ 健康检查
- ✅ 文档搜索功能
- ✅ 文档内容获取功能
- ✅ API响应时间和数据质量
- 运行get-long-term-token.js生成长期Token
- 运行test-api-connection.js验证API连接
- 在AI工具中注册MCP服务（见下方配置说明）
- 运行get-fresh-token.js或get-long-term-token.js生成新Token
- 运行update-env-token.js更新配置文件
- 重启MCP服务
- 运行test-api-connection.js进行全面测试
- 检查测试结果确保所有功能正常

- Windows:%APPDATA%\Cursor\User\globalStorage\cursor.mcp\config.json
- macOS:~/Library/Application Support/Cursor/User/globalStorage/cursor.mcp/config.json
- Linux:~/.config/Cursor/User/globalStorage/cursor.mcp/config.json

{ "ldims": { "command": "node", "args": ["D:/DEV/LDIMS/backend_mcp/dist/index.js"], "env": { "LDIMS_API_BASE_URL": "http://localhost:3000", "LDIMS_API_VERSION": "v1", "LDIMS_AUTH_TOKEN": "your_long_term_token_here", "NODE_ENV": "production" } } }

- Windows:%APPDATA%\Claude\claude_desktop_config.json
- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Linux:~/.config/Claude/claude_desktop_config.json

{ "mcpServers": { "ldims": { "command": "node", "args": ["D:/DEV/LDIMS/backend_mcp/dist/index.js"], "env": { "LDIMS_API_BASE_URL": "http://localhost:3000", "LDIMS_API_VERSION": "v1", "LDIMS_AUTH_TOKEN": "your_long_term_token_here", "NODE_ENV": "production" } } } }

- command: 使用node命令运行编译后的JavaScript文件
- args: 指向编译后的dist/index.js文件的绝对路径
- LDIMS_API_BASE_URL: 使用HTTP地址，不是文件路径（如：http://localhost:3000）
- LDIMS_AUTH_TOKEN: 使用get-long-term-token.js生成的长期Token
- NODE_ENV: 设置为production以获得最佳性能
- 路径必须使用绝对路径，根据您的实际安装位置调整
- 确保先运行npm run build编译项目
- 确保LDIMS后端服务在http://localhost:3000运行

- 确保LDIMS后端服务正在运行
- Token生成需要有效的数据库连接
- 测试脚本需要编译后的代码（先运行npm run build）
- 所有脚本都会读取项目根目录的.env文件
- 检查LDIMS后端服务状态
- 验证数据库连接
- 确认环境变量配置
- 查看控制台错误信息

Extract text content from local PDF, DOCX, and PPTX files to build a knowledge base.

An intelligent structured document management system designed for large language models.

Provides comprehensive access to an Obsidian vault, allowing AI agents to read, write, search, and manage notes via the Local REST API plugin.

Local-first MCP server that indexes folders, PDFs, code, and past AI conversations — and exposes them as a single grounded-search tool. Runs fully offline.

Manage notes and files in an Obsidian vault. Requires the Obsidian Local REST API plugin.

Interact with The Drive AI files directly from AI assistants like ChatGPT or Claude using the Model Context Protocol (MCP).

An MCP server for viewing, editing, and creating text files, based on the Claude built-in text editor tool.

A server for processing PDF files, allowing text and table extraction, metadata retrieval, and file listing within a specific directory.

A server providing comprehensive file system operations, automatically downloaded and built on first use.

A simple utility to combine multiple files into a single file.