io.github.roystondwork-dev/diskdiet
diskdiet
Is the diskdiet MCP server down? No. It is up and needs network, probed 2026-11-13.
See what developer caches and old node_modules use disk space, and free it safely.
needs network probed 2026-11-14 · unchanged since 2026-11-13
MCP error -32000: Connection closed diskdiet: downloading diskdiet 0.6.1 (diskdiet_0.6.1_linux_amd64.tar.gz)... diskdiet: fetch failed
- Run it
- npx -y diskdiet@0.6.1 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Repository
- https://github.com/roystondwork-dev/diskdiet
- Website
- https://github.com/roystondwork-dev/diskdiet/blob/main/docs/mcp.md
- Registry
- active, updated 2026-11-12 · registry entry
Compare this server with others.
More servers
Other registry entries on npmjs.com, the ones next to this name; all of them.
- Rove io.github.rove0752-byte/rove · alive
- rowstile io.github.rowstile/rowstile · alive
- Portveil io.github.roybogs/portveil-mcp · needs env
- Oura Ring (read-only) io.github.royreznik/oura-ring-mcp · alive
- portcheck io.github.roystondwork-dev/portcheck · needs network
- Jira Alerts (JSM Operations) io.github.rrvrs/jira-alerts-mcp · alive
- io.github.rsdouglas/janee · crashed on start
- Rootstock (RSK) MCP Server io.github.rsksmart/rsk-mcp-server · alive
Servers that mention developer or modules.
- Zaira Labs Guide ai.zairalabs/guide · alive
- Reviewder app.reviewder/reviewder · needs auth
- RideDesk Developer Docs app.ridedesk/docs · alive
- ai.smithery/neverinfamous-memory-journal-mcp · not found
- WarpLink app.warplink/warplink · needs auth
- ProfitCollector ca.bakhour/profitcollector · alive
- cn.pianam.mcp/devtools-mcp · alive
- coach.marian/eng-leadership-toolkit · alive
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server tries to reach the network on start. The probe runs in a container with the network off, so a server that connects lazily, on the first tool call, is measured.