fs-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fs-mcpsearch for 'TODO' in all Python files"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fs-mcp
Hosted filesystem MCP server over HTTP. Read, write, edit, grep, glob, and tree — deployable to Railway with a persistent volume.
Gap this fills
Every existing filesystem MCP server (including the official @modelcontextprotocol/server-filesystem with 248k weekly downloads) is stdio-only — it runs as a local subprocess. There is no hosted, HTTP-accessible filesystem MCP with auth. This fills that gap.
Tools
Tool | Description |
| Read file with line numbers, pagination (offset/limit) |
| Write/overwrite a file, creates parent dirs |
| Search-and-replace patch (safe: errors if >1 match unless replace_all) |
| Regex search across files with context lines |
| Find files by glob pattern, sorted by mtime |
| Directory tree (max_depth up to 6) |
| List directory with sizes and timestamps |
| Delete a single file |
Auth
All requests require Authorization: Bearer <MCP_AUTH_TOKEN>.
Environment variables
Var | Default | Description |
| (required) | Bearer token for auth |
|
| Filesystem root. Mount a Railway volume here. |
|
| HTTP port |
Deploy to Railway
# 1. Create project
railway login
railway init
# 2. Set env vars
railway variables set MCP_AUTH_TOKEN=$(openssl rand -hex 32)
railway variables set FS_ROOT=/data
# 3. Add a volume mounted at /data in Railway dashboard
# 4. Deploy
railway upConnect from Claude Desktop / any MCP client
{
"mcpServers": {
"fs-mcp": {
"transport": "http",
"url": "https://your-app.up.railway.app/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}Local dev
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
MCP_AUTH_TOKEN=dev FS_ROOT=./data PORT=8000 .venv/bin/python3 server.pyRelated MCP Connectors
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Build, deploy, and host full-stack web apps from any MCP client. DB, auth, storage, cron included.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.