Full current ResourceState: rate-limit windows (5h/7d remaining, reset times), context headroom (tokens before the compaction ceiling), burn rate, session cost. Use to ground planning in actual budgets.
AI agents call resource_state to retrieve information from Headroom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current state information about rate limits, context budgets, burn rates, and session costs. It is purely a read/query operation with no side effects — it fetches telemetry data to inform planning decisions. Severity is low as misuse only exposes operational metadata with no destructive or financial consequences.
From the tool's definition Full current ResourceState: rate-limit windows (5h/7d remaining, reset times), context headroom (tokens before the compaction ceiling), burn rate, session cost. Use to ground planning in actual budgets.
Attacks that exploit this kind of access
Full current ResourceState: rate-limit windows (5h/7d remaining, reset times), context headroom (tokens before the compaction ceiling), burn rate, session cost. Use to ground planning in actual budgets. It is categorised as a Read tool in the Headroom MCP Server, which means it retrieves data without modifying state.
Register the Headroom MCP server in PolicyLayer and add a rule for resource_state: 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 Headroom. Nothing to install.
resource_state 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 resource_state 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 resource_state. 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.
resource_state is provided by the Headroom MCP server (tyejcoleman/headroom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →