Combine and format Infracost JSON files. Useful for merging multiple cost estimates or converting formats. Requires infracost CLI to be installed.
AI agents call infracost_output to retrieve information from Infracost MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and formats existing JSON files, combining cost estimate data. It does not create, modify, delete, or execute anything — it only processes and presents existing data. The operation is read-only and non-destructive.
From the tool's definition Combine and format Infracost JSON files. Useful for merging multiple cost estimates or converting formats.
Attacks that exploit this kind of access
Combine and format Infracost JSON files. Useful for merging multiple cost estimates or converting formats. Requires infracost CLI to be installed. It is categorised as a Read tool in the Infracost MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Infracost MCP Server MCP server in PolicyLayer and add a rule for infracost_output: 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 Infracost MCP Server. Nothing to install.
infracost_output 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 infracost_output 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 infracost_output. 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.
infracost_output is provided by the Infracost MCP Server MCP server (phildougherty/infracost_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →