Medium Risk

create_snapshot

Create a snapshot (backup) of Elasticsearch indices with comprehensive options and repository management

How to control create_snapshot ↓

What create_snapshot does on Agent Knowledge MCP

AI agents use create_snapshot to create or update resources in Agent Knowledge MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Knowledge MCP environment.

Medium Risk

Why create_snapshot needs a policy

This tool creates backups of Elasticsearch indices, which is a reversible write operation (snapshots can be deleted or overwritten). It does not execute arbitrary code, destroy data irreversibly, move money, or fall into other categories. The 'comprehensive options and repository management' suggests it may modify index configurations, but the primary function is backup creation.

From the tool's definition Tool description states 'Create a snapshot (backup) of Elasticsearch indices' — snapshot creation modifies backup state and repository configuration, constituting a write operation that persists data in backup storage.

Documented attack patterns abuse exactly the kind of access create_snapshot gives an agent:

How to control create_snapshot

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Knowledge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_snapshot:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_snapshot": {
      "limits": [
        {
          "counter": "create_snapshot_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_snapshot stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Agent Knowledge MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_snapshot

What does the create_snapshot tool do? +

Create a snapshot (backup) of Elasticsearch indices with comprehensive options and repository management. It is categorised as a Write tool in the Agent Knowledge MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_snapshot? +

Register the Agent Knowledge MCP server in PolicyLayer and add a rule for create_snapshot: 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 Agent Knowledge MCP. Nothing to install.

What risk level is create_snapshot? +

create_snapshot is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_snapshot? +

Yes. Add a rate_limit block to the create_snapshot 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.

How do I block create_snapshot completely? +

Set action: deny in the PolicyLayer policy for create_snapshot. 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.

What MCP server provides create_snapshot? +

create_snapshot is provided by the Agent Knowledge MCP server (itshare4u/agentknowledgemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agent Knowledge MCP tool call.

Start from Agent Knowledge MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

27 Agent Knowledge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.