AI agents call tigris_get_signed_url_object to retrieve information from Tigris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (a signed URL) about an object—a read-only operation with no side effects. It does not create, modify, delete, or execute operations. The signed URL itself is a credential artifact, but generating it is fundamentally a read operation. The blast radius is minimal: misuse would only expose a URL that is likely time-limited and specific to one object.
From the tool's definition Tool name 'tigris_get_signed_url_object' and description 'Get an signed url of an object from a bucket' indicate a retrieval operation that generates a URL for accessing an existing object without modifying or deleting data.
Attacks that exploit this kind of access
Get an signed url of an object from a bucket. It is categorised as a Read tool in the Tigris MCP Server, which means it retrieves data without modifying state.
Register the Tigris MCP server in PolicyLayer and add a rule for tigris_get_signed_url_object: 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 Tigris. Nothing to install.
tigris_get_signed_url_object 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 tigris_get_signed_url_object 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 tigris_get_signed_url_object. 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.
tigris_get_signed_url_object is provided by the Tigris MCP server (@tigrisdata/tigris-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 →