io.github.edobusy/agenthold

agenthold

Is the agenthold MCP server down? Yes. It has given no valid answer since 2026-10-20: crashed on start.

Shared versioned state for multi-agent AI workflows

crashed on start down since 2026-10-20 · probed 2026-11-14 · unchanged since 2026-10-27

MCP error -32000: Connection closed
error: unable to open database file

Run it: uvx agenthold@0.10.0 (stdio, probed in a container with the network off)
Host: pypi.org
Repository: https://github.com/edobusy/agenthold
Website: https://github.com/edobusy/agenthold#readme
Registry: active, updated 2026-07-07 · registry entry

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Decompose io.github.echology-io/decompose · timeout
io.github.ed-dryha/reolink-mcp · needs env
alethech io.github.eddyflores100-lang/alethech · crashed on start
MCHS NWAU Calculator io.github.edithatogo/mchs · crashed on start
HirePulse tools io.github.edtool79-collab/hirepulse-open-source · crashed on start
io.github.eduplopez/mcp-voice-summary · alive
Runspector — AI running coach for Garmin io.github.edxleon/runspector · alive
Lomberk io.github.ege-usta/lomberk · needs env

Servers that mention versioned or workflows.

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

No valid answer since 2026-10-20, in every probe since then.
The process exited on start before it answered initialize. The error output is above.