claims_stealable

List all stealable issues 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.

Server Claude Flow claude-flow
Category Read
Risk class Low
Parameters 00 required

What claims_stealable does on Claude Flow

AI agents call claims_stealable to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why claims_stealable needs a policy

The tool's primary action is listing stealable issues, which is a read operation. However, the context is security-sensitive: it exposes information about which capability claims can be stolen or hijacked by agents, potentially enabling privilege escalation.

From the tool's definition "List all stealable issues" — the tool lists/enumerates stealable claims or issues, which is a read/query operation.

Risk signalsAdmin/system-level operation

Questions about claims_stealable

What does the claims_stealable tool do? +

List all stealable issues 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 Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on claims_stealable? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for claims_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_stealable? +

claims_stealable is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit claims_stealable? +

Yes. Add a rate_limit block to the claims_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_stealable completely? +

Set action: deny in the PolicyLayer policy for claims_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_stealable? +

claims_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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.