Skip to main content
Glama
VitexSoftware

mcp-server-filesystem

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FS_ROOTNoDirectory all paths are confined to (default: current working directory at startup)
FS_READONLYNoSet to 'false' to allow writes/deletes/moves; otherwise, blocks mutating tools.true

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_dirA

List the contents of a directory (name, is_dir, size, mtime).

read_fileA

Read a file's contents.

Text files are decoded with encoding (errors replaced). Set binary=True to get the raw bytes base64-encoded instead. Reads are capped at max_bytes to avoid dumping huge files into context.

statC

Fetch filesystem metadata for a path.

existsB

Check whether a path exists.

glob_searchA

Search for files matching a glob pattern (e.g. **/*.py) under path.

write_fileB

Write text content to a file. Requires FS_READONLY=false.

mkdirB

Create a directory. Requires FS_READONLY=false.

deleteA

Delete a file, or a directory if recursive=True. Requires FS_READONLY=false.

moveB

Move/rename a file or directory. Requires FS_READONLY=false.

copyB

Copy a file, or a directory if recursive=True. Requires FS_READONLY=false.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/VitexSoftware/mcp-server-filesystem'

If you have feedback or need assistance with the MCP directory API, please join our Discord server