Lists files in a GCS bucket
AI agents call list_gcs_files to retrieve information from FlexFS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns directory/bucket contents without creating, modifying, deleting, or executing anything. It has minimal blast radius—an AI agent listing GCS files poses no risk of data loss, unauthorized writes, or external operations. The only concern is potential information disclosure if the bucket contains sensitive file names, but that is a read-level risk.
From the tool's definition Tool name 'list_gcs_files' and description 'Lists files in a GCS bucket' indicate a retrieval operation with no modification or deletion capabilities.
Attacks that exploit this kind of access
Lists files in a GCS bucket. It is categorised as a Read tool in the FlexFS MCP MCP Server, which means it retrieves data without modifying state.
Register the FlexFS MCP server in PolicyLayer and add a rule for list_gcs_files: 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 FlexFS MCP. Nothing to install.
list_gcs_files 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 list_gcs_files 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 list_gcs_files. 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.
list_gcs_files is provided by the FlexFS MCP server (linn-latt/flexfs-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 →