Filesystem
Filesystem MCP Server provides secure, controlled filesystem operations for AI agents like Cline, operating strictly within a project's root directory. Developed by shtse8, this TypeScript implementation uses Node.js's native filesystem modules to offer tools for listing, reading, writing, copying, moving, and searching files with robust path validation to prevent traversal outside the project boundary. The server determines the project root from its current working directory, enabling context-specific operations when launched correctly by the host environment. With features like batch processing, indentation preservation during edits, and detailed error reporting, it's particularly valuable for AI coding assistants that need to safely manipulate project files without unrestricted filesystem access.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/sylphxai/filesystem-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
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.