Context-safe usage audit query. Defaults to aggregated summary, supports precise search by execution_id/search_id/charge_outcome/credit range, and writes large exports to a local JSONL file instead of returning all rows.
AI agents call usage_history to retrieve information from Qveris Agent Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves historical usage and audit information with optional filtering parameters (execution_id, search_id, charge_outcome, credit range) and outputs results either as summaries or exports. This is a classic read operation with no side effects on the underlying system state or financial transactions.
From the tool's definition Tool description explicitly states 'audit query' and 'search', with outputs either returned as aggregated summary or written to local file. No modification, deletion, or execution of external operations—purely data retrieval and reporting.
Documented attack patterns abuse exactly the kind of access usage_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qveris Agent Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for usage_history:
{
"version": "1",
"default": "deny",
"tools": {
"usage_history": {}
}
}usage_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Context-safe usage audit query. Defaults to aggregated summary, supports precise search by execution_id/search_id/charge_outcome/credit range, and writes large exports to a local JSONL file instead of returning all rows. It is categorised as a Read tool in the Qveris Agent Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Qveris Agent Toolkit MCP server in PolicyLayer and add a rule for usage_history: 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 Qveris Agent Toolkit. Nothing to install.
usage_history 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 usage_history 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 usage_history. 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.
usage_history is provided by the Qveris Agent Toolkit MCP server (qverisai/qveris-agent-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Qveris Agent Toolkit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Qveris Agent Toolkit tools catalogued and risk-classified — across an index of 42,500+ MCP servers.