ralph_hero__capture_snapshot · Ralph Hero MCP: Risk & Policy

WHAT IT DOES

What ralph_hero__capture_snapshot does on Ralph Hero

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

WHY IT NEEDS A POLICY

Why ralph_hero__capture_snapshot needs a policy

The tool captures a snapshot and appends it to a file. It is a write operation (append-only to a JSONL file) with no destructive or financial implications. Misuse could result in excessive disk usage or spamming of snapshot files, but effects are reversible (files can be deleted). Severity is medium because it writes to the local filesystem and performs a full project scan.

From the tool's definition append it to the partitioned JSONL file at ~/.ralph-hero/snapshots/<owner>/<projectNumber>.jsonl ... Append-only, schema-versioned. Returns the snapshot row that was written.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ralph_hero__capture_snapshot Rate-limited

ralph_hero__capture_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": {
    "ralph_hero__capture_snapshot": {
      "limits": [
        {
          "counter": "ralph_hero__capture_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 Ralph Hero, so you can run agents against it safely.

FAQ

Questions about ralph_hero__capture_snapshot

What does the ralph_hero__capture_snapshot tool do? +

Capture a single point-in-time snapshot of the project dashboard + metrics and append it to the partitioned JSONL file at ~/.ralph-hero/snapshots/<owner>/<projectNumber>.jsonl. Fetches all project items (full project scan, no silent 500-cap) so per-phase WIP and totals reflect every item regardless of board position. Append-only, schema-versioned. Returns the snapshot row that was written. It is categorised as a Write tool in the Ralph Hero MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ralph_hero__capture_snapshot? +

Register the Ralph Hero MCP server in PolicyLayer and add a rule for ralph_hero__capture_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 Ralph Hero. Nothing to install.

What risk level is ralph_hero__capture_snapshot? +

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

Can I rate-limit ralph_hero__capture_snapshot? +

Yes. Add a rate_limit block to the ralph_hero__capture_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 ralph_hero__capture_snapshot completely? +

Set action: deny in the PolicyLayer policy for ralph_hero__capture_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 ralph_hero__capture_snapshot? +

ralph_hero__capture_snapshot is provided by the Ralph Hero MCP server (ralph-hero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.