Reads a file from Google Cloud Storage
AI agents call read_gcs_file 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 retrieves data from cloud storage without side effects. It is a read-only operation that queries or fetches content. No data is created, modified, deleted, or financial transactions are involved. The severity is low because reading files is generally safe; misuse would expose only what the AI can already access within GCS permissions.
From the tool's definition Tool name and description both indicate 'Reads a file from Google Cloud Storage' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Reads a file from Google Cloud Storage. 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 read_gcs_file: 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.
read_gcs_file 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 read_gcs_file 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 read_gcs_file. 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.
read_gcs_file 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 →