largefile
Verified Safeby peteretelej
Overview
Enables AI assistants to interact with large text files by providing tools for structured analysis, targeted reading, pattern searching, and atomic editing, circumventing typical context window limitations.
Installation
uvx --from largefile largefile-mcpEnvironment Variables
- LARGEFILE_MEMORY_THRESHOLD_MB
- LARGEFILE_MMAP_THRESHOLD_MB
- LARGEFILE_MAX_LINE_LENGTH
- LARGEFILE_TRUNCATE_LENGTH
- LARGEFILE_FUZZY_THRESHOLD
- LARGEFILE_MAX_SEARCH_RESULTS
- LARGEFILE_CONTEXT_LINES
- LARGEFILE_SIMILAR_MATCH_LIMIT
- LARGEFILE_SIMILAR_MATCH_THRESHOLD
- LARGEFILE_STREAMING_CHUNK_SIZE
- LARGEFILE_BACKUP_DIR
- LARGEFILE_MAX_BACKUPS
- LARGEFILE_MAX_BATCH_CHANGES
- LARGEFILE_ENABLE_TREE_SITTER
- LARGEFILE_TREE_SITTER_TIMEOUT
- LARGEFILE_LOG_LEVEL
- LARGEFILE_ENABLE_METRICS
- LARGEFILE_LOG_FILE
- LARGEFILE_ENABLE_PARALLEL_SEARCH
- LARGEFILE_ENABLE_AST_CACHE
Security Notes
The server operates via standard I/O (stdio), limiting direct network exposure. File operations use robust path normalization (os.path.abspath, os.path.expanduser) and atomic writes (temp file + rename) for integrity. It utilizes well-vetted third-party libraries like `tree-sitter` for semantic parsing and `rapidfuzz` for fuzzy matching. No hardcoded credentials or malicious patterns like unvalidated `eval()` of user input were found in the core server logic. Backups are automatically created before edits, providing a safety net for destructive operations.
Similar Servers
code-index-mcp
Intelligent code indexing and analysis for Large Language Models, enabling tasks such as code review, refactoring, documentation generation, debugging assistance, and architectural analysis.
chunkhound
Local-first codebase intelligence tool for AI assistants, extracting architecture, patterns, and institutional knowledge at any scale via Model Context Protocol (MCP).
consult7
Enables AI agents to analyze extensive file collections (e.g., codebases) using large context window models via OpenRouter, overcoming agent context limits.
aleph
Enables AI assistants to analyze documents too large for their context window by providing tools for search, exploration, and computation over massive datasets, implementing a Recursive Language Model (RLM) approach.