Provides precise, content-anchored file editing and robust access control for AI agents operating on file systems.
Sponsored
Hashfile offers a powerful Model Context Protocol (MCP) server designed to give AI agents surgical precision over file editing and ironclad control over file access. It addresses the common problem of line-number-based editing failures by implementing content-anchored operations, where every line is tagged with a content hash, ensuring edits target the *right content* regardless of file changes. This server also introduces AGENTS.md, a declarative system for granular access control, allowing developers to forbid access to secrets, establish read-only permissions for critical files, and ignore irrelevant build artifacts or dependencies from AI context. With full compatibility for standard MCP filesystem tools, Hashfile provides a reliable and secure foundation for AI-driven development workflows.
Key Features
01Nine essential MCP tools for file system interaction
02Hash-Anchored Editing for reliable, content-based code modifications
03Fuzzy Line Matching to locate moved lines after file changes
04AGENTS.md Support for declarative, hierarchical access control
05Automatic .gitignore integration for context filtering
062 GitHub stars
Use Cases
01Enabling AI agents to perform reliable and precise code modifications in dynamic projects without line-number errors.
02Implementing granular access control to prevent AI agents from accessing or modifying sensitive files like secrets or lock files.
03Filtering irrelevant files and directories (e.g., node_modules, build artifacts) from AI context to improve focus and token efficiency.
