Estimates costs for multiple LLM tasks in a single call. Each task can provide prompt_text, a task description, or explicit token counts. Returns per-task token-resolution metadata, aggregate totals, and the cheapest context-compatible model for the whole batch.
High parameter count (13 properties); Single-target operation
Part of the TokenOracle MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call estimate_cost_batch 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 estimate_cost_batch 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:
estimate_cost_batch:
rules:
- action: allowSee the full TokenOracle policy for all 9 tools.
Agents calling read-class tools like estimate_cost_batch 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.
Estimates costs for multiple LLM tasks in a single call. Each task can provide prompt_text, a task description, or explicit token counts. Returns per-task token-resolution metadata, aggregate totals, and the cheapest context-compatible model for the whole batch.. It is categorised as a Read tool in the TokenOracle MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for estimate_cost_batch. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the TokenOracle MCP server.
estimate_cost_batch 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 estimate_cost_batch 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 estimate_cost_batch. 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.
estimate_cost_batch is provided by the TokenOracle MCP server (token-oracle-mcp). 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