Get agent load information 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.
AI agents call claims_load 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.
This tool queries agent load status to inform access-control decisions. It has no side effects—it does not grant, modify, or terminate privileges (those are distinct tools: claims_grant, agent_terminate). The severity is low because unauthorized reads of load metrics pose minimal risk compared to execution or destructive operations.
From the tool's definition "Get agent load information" — the tool retrieves load data. Description emphasizes use in capability gating and checking (read operations) rather than modification: "Pair claims_grant + claims_check before letting an agent run privileged ops." The word…
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get agent load information 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.
Register the Claude Flow MCP server in PolicyLayer and add a rule for claims_load: 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.
claims_load is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the claims_load 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.
Set action: deny in the PolicyLayer policy for claims_load. 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.
claims_load 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.