Run a runbook against one or more environments in Octopus Deploy. Runbooks execute operational processes (DB backups, smoke tests, environment refresh, etc.) against the specified environments. For tenanted runs, supply tenants and/or tenantTags. Two project kinds: - DB-backed projects: by defaul...
AI agents invoke run_runbook to trigger actions in Octopus Deploy MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of runbooks—operational automation scripts—against live environments. While not immediately destructive, runbooks can perform critical operations (database backups, environment refreshes) whose effects depend on the runbook configuration and cannot always be predicted by the AI.
From the tool's definition The tool 'run_runbook' executes operational processes including 'DB backups, smoke tests, environment refresh, etc.' against specified environments.
Documented attack patterns abuse exactly the kind of access run_runbook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Octopus Deploy MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_runbook:
{
"version": "1",
"default": "deny",
"tools": {
"run_runbook": {
"limits": [
{
"counter": "run_runbook_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_runbook stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run a runbook against one or more environments in Octopus Deploy. Runbooks execute operational processes (DB backups, smoke tests, environment refresh, etc.) against the specified environments. For tenanted runs, supply tenants and/or tenantTags. Two project kinds: - DB-backed projects: by default the runbook. It is categorised as a Execute tool in the Octopus Deploy MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Octopus Deploy MCP Server MCP server in PolicyLayer and add a rule for run_runbook: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Octopus Deploy MCP Server. Nothing to install.
run_runbook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_runbook rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_runbook. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_runbook is provided by the Octopus Deploy MCP Server MCP server (octopusdeploy/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Octopus Deploy MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Octopus Deploy MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.