get_reservation_details
Get Compute Engine reservation details. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation properties like VM family and reserved resources, commitment and linked c...
This record as markdown: /tools/com-googleapis-compute-mcp/get-reservation-details.md
What get_reservation_details does on Mcp
AI agents call get_reservation_details to retrieve information from Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Required. Identifier. Name of the reservation to retrieve. |
zone | string | Yes | Required. The zone of the reservation. |
project | string | Yes | Required. Project ID for this request. |
Parameters from the server's own tool schema.
Why get_reservation_details is rated Low
This tool purely queries and retrieves existing reservation metadata without creating, modifying, or deleting resources. The verb 'Get' and passive 'Returns' indicate a read-only operation. The required inputs (project, zone, reservation name) are lookup parameters, not configuration changes. Blast radius is minimal—misuse would only expose infrastructure information already owned by the project.
From the tool's definition Tool description uses 'Get' and 'Returns reservation details' with no modifications, deletions, or side effects mentioned. It retrieves information about Compute Engine reservations including name, ID, status, timestamps, and configuration properties.
Attacks that exploit this kind of access
The rule that runs get_reservation_details safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_reservation_details, this is the rule to start with:
get_reservation_details 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 Mcp, apply this rule, and every get_reservation_details call is checked against it from then on.
Questions about get_reservation_details
Get Compute Engine reservation details. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation properties like VM family and reserved resources, commitment and linked commitments, sharing settings, and resource status. Requires project, zone, and reservation name as input. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
get_reservation_details accepts 3 parameters: name, zone, project. Required: name, zone, project. The full parameter table on this page comes from the server's own tool schema.
Register the MCP server in PolicyLayer and add a rule for get_reservation_details: 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 Mcp. Nothing to install.
get_reservation_details 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 get_reservation_details 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 get_reservation_details. 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.
get_reservation_details is provided by the MCP server (https://compute.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on , and thousands of servers like it.
This server
Across the catalogue