// SCAN REPORT

Runbook

4 tools. 4 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

4 can modify or destroy data

0 read-only

4 tools total

Community server · catalogue entry verified 29/06/2026

How to control Runbook ↓

TOOL MAP

What Runbook exposes to your agents

Read (0) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Runbook tools

Destructive · High delete_runbook The tool is named delete_runbook, which signals permanent removal of runbook resources. Write · Medium create_runbook Creating files is a reversible write operation. Write · Medium create_runbook_log The tool creates logs related to runbook execution, which is a write operation that produces new records. Write · Medium reindex_runbooks The name 'reindex_runbooks' suggests a maintenance operation that rebuilds or updates an index of runbooks.

4 of Runbook's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Runbook

PolicyLayer is an MCP gateway — it sits between your AI agents and Runbook, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_runbook": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_runbook": {
    "limits": [
      {
        "counter": "create_runbook_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Runbook — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RUNBOOK →

Instant setup, no code required.

FULL CATALOGUE

All 4 Runbook tools

DESTRUCTIVE 1 tools

Destructive delete_runbook delete_runbook

WRITE 3 tools

Write create_runbook Create a runbook file and save the content. Write create_runbook_log create_runbook_log Write reindex_runbooks reindex_runbooks

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Runbook

Can an AI agent delete data through the Runbook MCP server? +

Yes. The Runbook server exposes 1 destructive tools including delete_runbook. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Runbook? +

The Runbook server has 3 write tools including create_runbook, create_runbook_log, reindex_runbooks. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Runbook.

How many tools does the Runbook MCP server expose? +

4 tools across 2 categories: Destructive, Write. 0 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Runbook? +

Register the Runbook MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Runbook tool call.

Deterministic rules across all 4 Runbook tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RUNBOOK →

Instant setup, no code required.

4 Runbook tools catalogued and risk-classified — across an index of 43,000+ MCP servers.