save_snapshot · Trailmark MCP Server MCP: Risk & Policy

WHAT IT DOES

What save_snapshot does on Trailmark MCP Server

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

WHY IT NEEDS A POLICY

Why save_snapshot needs a policy

This tool creates or modifies snapshot files by persisting graph state. While it is a write operation, it is reversible (snapshots can be deleted or overwritten), so it does not qualify as Destructive. The severity is medium because unintended snapshot creation could consume disk space or overwrite important analysis state, but the impact is localized to the repository's snapshot directory and reversible.

From the tool's definition Tool description explicitly states "Persist the current graph state under .trailmark/snapshots" which involves creating/storing data in the file system. The verb 'persist' indicates writing/saving operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_snapshot Rate-limited

save_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_snapshot": {
      "limits": [
        {
          "counter": "save_snapshot_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Trailmark MCP Server, so you can run agents against it safely.

FAQ

Questions about save_snapshot

What does the save_snapshot tool do? +

Persist the current graph state under .trailmark/snapshots. It is categorised as a Write tool in the Trailmark MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_snapshot? +

Register the Trailmark MCP Server MCP server in PolicyLayer and add a rule for save_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 Trailmark MCP Server. Nothing to install.

What risk level is save_snapshot? +

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

Can I rate-limit save_snapshot? +

Yes. Add a rate_limit block to the save_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 save_snapshot completely? +

Set action: deny in the PolicyLayer policy for save_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 save_snapshot? +

save_snapshot is provided by the Trailmark MCP Server MCP server (parsiya/trailmark-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.