AI agents call fit_check 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.
The fit_check tool only reads and reports on current resource budgets and constraints. It does not modify, execute, delete, or commit any resources. It is purely informational, designed to help an AI agent understand whether work will fit within constraints before attempting it. No irreversible changes, code execution, or financial implications are involved.
From the tool's definition Tool performs a check operation that 'returns fits | tight | exceeds | defer per budget, plus advice' with no side effects mentioned. The description indicates it queries current budget state and provides information, similar to a 'get' or 'status' operation.
Attacks that exploit this kind of access
Check whether work estimated at est_tokens (optionally est_calls) fits current budgets. Returns fits | tight | exceeds | defer per budget, plus advice. Call before starting sizable tasks. 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 fit_check: 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.
fit_check 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 fit_check 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 fit_check. 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.
fit_check 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 →