Filesystem
Filesystem MCP Server provides a secure interface for AI agents to interact with local filesystems through standardized tools. Developed by Casey Hand (@cyanheads), this TypeScript implementation offers essential file operations including reading, writing, updating, and managing directories with robust path resolution, error handling, and logging. The server maintains session state for relative path resolution and implements comprehensive security measures like path sanitization and validation. It's particularly useful for AI workflows requiring file manipulation, code generation, or document analysis while maintaining a clean separation between AI agents and the underlying filesystem.
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/cyanheads/filesystem-mcp-server
- 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.