Aegis-File
Aegis-File-MCP-Server
claude mcp add --transport stdio cjxzyy-aegis-file-mcp-server docker run -i aegis-file-mcp-server:latest \ --env DB_URL="postgresql://user:password@localhost:5432/aegis_file" \ --env GO_ENV="production" \ --env TLS_KEY="<path-or-content>" \ --env TLS_CERT="<path-or-content>" \ --env REDIS_URL="redis://localhost:6379"
How to use
Aegis-File MCP Server is a local, plugin-enabled MCP server that bridges large language models with a structured local file system. It supports multiple MCP communication modes (stdio, SSE, and HTTP) and focuses on safe, incremental document parsing, structured knowledge extraction, and offline AI-ready processing. The server is designed to run locally with a lightweight monolith architecture and a plugin mechanism that can be embedded into existing systems. You can operate it via a containerized deployment or directly in your environment if you prefer a native Go-based setup. The included capabilities include intelligent document parsing across multiple formats, incremental synchronization, static and dynamic factor extraction, layered summarization, and local TLS 1.3 encryption with AES-256 file encryption for security. Tools and capabilities you’ll typically use include the MCP protocol adapter for Go, a local document parsing engine, a lightweight AI-ready processing pipeline, and the plugin system that enables extending functionality within your own environment.
How to install
Prerequisites:
- Go 1.22+ installed (for building/running the server locally)
- Python 3.11+ (AI/解析任务所需)
- PostgreSQL 16+ (结构化数据存储)
- Redis 7.2+ (本地缓存)
- Git (clone the仓库)
- Clone the repository
bash git clone https://github.com/your-org/cjxzyy-aegis-file-mcp-server.git cd cjxzyy-aegis-file-mcp-server
- Install Go and build/run locally
- Ensure Go is installed and in PATH
- Build the server (示例用法,按项目实际路径可能略有不同)
bash
将工作路径切换到项目根目录后运行以下命令来启动本地服务
go run cmd/server/main.go
- Prepare services
- Ensure PostgreSQL and Redis are running and accessible
- Create/prepare the required数据库和表格 according to the project schema
- 配置文件与环境变量
- 使用 configs/ 目录中的示例配置文件,或按实际环境创建自定义配置
- 必要时设置环境变量:DB_URL、REDIS_URL、TLS_CERT、TLS_KEY 等
- 运行方式(容器化可选)
- 参考上面的 mcp_config 使用 docker 运行镜像:aegis-file-mcp-server:latest
- 或直接在本地执行 go run cmd/server/main.go
- 验证运行
- 通过 MCP 客户端与服务器建立连接,检查 stdio/SSE/HTTP 模式的通信是否正常
- 确认 TLS、AES-256 加密等安全功能是否按预期工作
Additional notes
Tips and common issues:
- 数据库/缓存连接失败时,请检查本地网络与防火墙设置,确保 PostgreSQL 和 Redis 服务可达。
- TLS 1.3 加密需要正确配置 TLS 证书和私钥,确保证书链有效且路径可读取。
- 插件功能的稳定性依赖于插件版本与 Go/Python 运行时环境的一致性,建议在生产环境使用严格版本控制。
- MCP 协议适配层可能需要根据你的部署场景选择 stdio、SSE 或 HTTP 模式,请确保客户端与服务器端协商一致。
- 如果你使用容器化部署,确保挂载的配置文件和证书路径在容器内可访问,同时数据库和缓存的连接字符串不要泄露在镜像中。
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go