File Context Server
@bsmi021
A Model Context Protocol (MCP) server that provides file system context to Large Language Models (LLMs). This server enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.
Overview
What is File Context Server?
A Model Context Protocol (MCP) server that provides file system context to Large Language Models, enabling them to read, search, and analyze code files with advanced caching and real-time file watching.
How to use File Context Server?
Install via Smithery automatic installation or manually with npm install @modelcontextprotocol/file-context-server. Start the server with npx file-context-server and use tools such as list_context_files, read_context, search_context, analyze_code, and cache_stats with specified JSON parameters.
Key features of File Context Server
- File operations with recursive traversal and encoding support
- Code analysis: complexity, dependencies, and quality metrics
- Smart LRU caching with automatic invalidation and limits
- Advanced regex search with context and file type filtering
- Real-time file watching and cache invalidation
Use cases of File Context Server
- Provide LLMs with file contents and directory structure for code understanding
- Analyze code quality and complexity across a project
- Search for patterns or functions in large codebases with context
- Monitor file changes and automatically update cached context
FAQ from File Context Server
How do I install File Context Server?
You can install it automatically via Smithery using npx -y @smithery/cli install @bsmi021/mcp-file-context-server --client claude or manually with npm install @modelcontextprotocol/file-context-server.
What runtime dependencies does File Context Server require?
It requires Node.js and npm to install and run; no additional runtime or database is needed as it operates on the local file system.
Where does File Context Server store its data?
All data is read directly from the user’s local file system; cached entries are kept in memory with configurable size and TTL (default: 1000 entries, 1 hour).
What are the known limits of File Context Server?
Maximum file size for reading is configurable via the MAX_FILE_SIZE environment variable, and cache size is limited by MAX_CACHE_SIZE (default 1000 entries). The server returns specific error codes for issues like missing files or permission denials.
