cost_model
Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk).
This record as markdown: /tools/dev-dualregistry-registry/cost-model.md
What cost_model does on Dual Registry
AI agents call cost_model to retrieve information from Dual Registry without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why cost_model is rated Low
Even though cost_model only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs cost_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dual Registry, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cost_model, this is the rule to start with:
cost_model is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Dual Registry, apply this rule, and every cost_model call is checked against it from then on.
Questions about cost_model
Zero marginal cost model — which ops are free to replicate vs real cost (probe/composition/Talk). It is categorised as a Read tool in the Dual Registry MCP Server, which means it retrieves data without modifying state.
Register the Dual Registry MCP server in PolicyLayer and add a rule for cost_model: 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 Dual Registry. Nothing to install.
cost_model 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 cost_model 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 cost_model. 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.
cost_model is provided by the Dual Registry MCP server (https://www.dualregistry.dev/api/protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dual Registry, and thousands of servers like it.
This server
Across the catalogue