Browse files and folders at an S3 URI.
AI agents call browse_s3 to retrieve information from NGS360 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Browsing S3 URIs retrieves file and folder metadata without creating, modifying, deleting, or executing any operations. This is a passive information retrieval action with no side effects. The low severity reflects that exposure of this tool poses minimal risk — an AI agent using it can only list or view existing objects, not alter data or trigger external operations.
From the tool's definition Tool name is 'browse_s3' and description states 'Browse files and folders at an S3 URI' — the verb 'browse' indicates read-only access to list or view directory contents without modification.
Attacks that exploit this kind of access
Browse files and folders at an S3 URI. It is categorised as a Read tool in the NGS360 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NGS360 MCP Server MCP server in PolicyLayer and add a rule for browse_s3: 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 NGS360 MCP Server. Nothing to install.
browse_s3 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 browse_s3 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 browse_s3. 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.
browse_s3 is provided by the NGS360 MCP Server MCP server (ngs360/mcp-server). 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 →