What it does
The server takes scripts defined in a runbooks.json file and serves them as MCP tools. Each tool is typed and drawn from an allowlist, so the scripts an agent can call are those listed in the runbook file.
It suits cases where an agent should run predefined operational scripts through structured tool definitions rather than arbitrary commands. The source material does not describe setup steps or the environment needed to run it.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source
io.github.puglieseweb/systemdox-runbooks
Your runbooks as agent tools: scripts from runbooks.json served as typed, allowlisted MCP tools.
v0.1.11As shown on registry.modelcontextprotocol.io when we last read it