claims_mark-stealable · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What claims_mark-stealable does on Claude Flow

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

WHY IT NEEDS A POLICY

Why claims_mark-stealable needs a policy

This tool modifies security-relevant metadata (marking issues as stealable and managing capability claims) that affects which agents can perform privileged operations. While not immediately destructive, marking resources as stealable could enable unauthorized access by other agents, making it a Write operation with high severity due to its role in access control.

From the tool's definition Tool description states 'Mark an issue as stealable by other agents' and involves capability gating and privileged operations authorization. The term 'mark' indicates modification of state/metadata.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claims_mark-stealable Rate-limited

claims_mark-stealable 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": {
    "claims_mark-stealable": {
      "limits": [
        {
          "counter": "claims_mark-stealable_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 Flow, so you can run agents against it safely.

FAQ

Questions about claims_mark-stealable

What does the claims_mark-stealable tool do? +

Mark an issue as stealable by other agents Use when nothing native covers per-agent capability gating — Claude Code agents have file-system access by default. Pair claims_grant + claims_check before letting an agent run privileged ops. For trusted in-session work, no claims call is needed. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on claims_mark-stealable? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for claims_mark-stealable: 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 Flow. Nothing to install.

What risk level is claims_mark-stealable? +

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

Can I rate-limit claims_mark-stealable? +

Yes. Add a rate_limit block to the claims_mark-stealable 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 claims_mark-stealable completely? +

Set action: deny in the PolicyLayer policy for claims_mark-stealable. 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 claims_mark-stealable? +

claims_mark-stealable is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.