Query cost breakdown by provider, model, session, or day
Part of the LLMKit MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call llmkit_cost_query to retrieve information from LLMKit 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 llmkit_cost_query 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.
tools:
llmkit_cost_query:
rules:
- action: allowSee the full LLMKit policy for all 6 tools.
Agents calling read-class tools like llmkit_cost_query have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Query cost breakdown by provider, model, session, or day. It is categorised as a Read tool in the LLMKit MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for llmkit_cost_query. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the LLMKit MCP server.
llmkit_cost_query 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 llmkit_cost_query rule in your Intercept 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 Intercept policy for llmkit_cost_query. 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.
llmkit_cost_query is provided by the LLMKit MCP server (smigolsmigol/llmkit). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept