save_summary · Claude Team MCP: Risk & Policy

WHAT IT DOES

What save_summary does on Claude Team MCP

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

WHY IT NEEDS A POLICY

Why save_summary needs a policy

This tool creates or stores a summary record, which is a reversible write operation with no side effects on core project data, no code execution, and no data deletion. It fits the Write category as it modifies stored state (the summary) without destructive or executable consequences. Severity is low because misuse would only affect summary metadata, not critical project integrity.

From the tool's definition Tool name 'save_summary' and description 'Save a compact progress summary' indicate creating/writing a summary document. The TOKEN-SAVING note confirms it modifies state by persisting data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_summary Rate-limited

save_summary 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_summary": {
      "limits": [
        {
          "counter": "save_summary_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 Claude Team MCP, so you can run agents against it safely.

FAQ

Questions about save_summary

What does the save_summary tool do? +

Save a compact progress summary. TOKEN-SAVING: write a summary when context. It is categorised as a Write tool in the Claude Team 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 save_summary? +

Register the Claude Team MCP server in PolicyLayer and add a rule for save_summary: 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 Claude Team MCP. Nothing to install.

What risk level is save_summary? +

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

Can I rate-limit save_summary? +

Yes. Add a rate_limit block to the save_summary 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_summary completely? +

Set action: deny in the PolicyLayer policy for save_summary. 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_summary? +

save_summary is provided by the Claude Team MCP server (lakshan12367/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.