Checks whether a planned LLM task fits within a monthly budget. Accepts prompt_text, task descriptions, or explicit token counts. Returns a go/no-go decision, resolved token counts, and ranked cheaper alternatives that can actually fit the request.
Risk signalsHigh parameter count (12 properties)
Part of the TokenOracle server.
Free to start. No card required.
AI agents call budget_check to retrieve information from TokenOracle without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though budget_check only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"budget_check": {}
}
}See the full TokenOracle policy for all 9 tools.
These attack patterns abuse exactly the kind of access budget_check gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Checks whether a planned LLM task fits within a monthly budget. Accepts prompt_text, task descriptions, or explicit token counts. Returns a go/no-go decision, resolved token counts, and ranked cheaper alternatives that can actually fit the request.. It is categorised as a Read tool in the TokenOracle MCP Server, which means it retrieves data without modifying state.
Register the TokenOracle MCP server in PolicyLayer and add a rule for budget_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 TokenOracle. Nothing to install.
budget_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 budget_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 budget_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.
budget_check is provided by the TokenOracle MCP server (VictoryInTech/TokenOracle-MCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 TokenOracle tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.