Call after LLM invocations to record actual token usage. Cost is computed server-side using current provider pricing — no manual rate lookup needed. The recorded data feeds burnrate_budget projections and spend alerts. Returns the computed cost in USD and whether pricing was found for the model. ...
Part of the Plith MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call burnrate_track to retrieve information from Plith 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 burnrate_track 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:
burnrate_track:
rules:
- action: allowSee the full Plith policy for all 14 tools.
Agents calling read-class tools like burnrate_track 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.
Call after LLM invocations to record actual token usage. Cost is computed server-side using current provider pricing — no manual rate lookup needed. The recorded data feeds burnrate_budget projections and spend alerts. Returns the computed cost in USD and whether pricing was found for the model. Use burnrate_budget to see cumulative daily spend. Supports anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Free — no credits charged.. It is categorised as a Read tool in the Plith MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for burnrate_track. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Plith MCP server.
burnrate_track 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 burnrate_track 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 burnrate_track. 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.
burnrate_track is provided by the Plith MCP server (plith/plith). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.