Filesystem
A Go implementation of the Model Context Protocol (MCP) that enables seamless integration between LLM applications and local filesystem resources. This server provides secure, controlled access to files and directories through a set of tools for browsing, reading, writing, and manipulating filesystem content. It features robust path validation to prevent unauthorized access, supports various file types including text and images, and handles large files appropriately through resource references. Built as a learning project based on the mark3labs implementation, it's useful for AI applications that need to interact with local files while maintaining security boundaries.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/qiangmzsx/mcp-filesystem-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Filesystem from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.