生成预签名 URL
AI agents call tos_presigned_url to retrieve information from TOS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Pre-signed URL generation is a read-like operation that produces access credentials without creating, modifying, or deleting data. It retrieves or computes authorization tokens. While the generated URL could be used for Write/Execute/Destructive operations downstream, the tool itself only generates the URL artifact.
From the tool's definition Tool name 'tos_presigned_url' and description '生成预签名 URL' (Generate pre-signed URL) indicate URL generation for access; no data modification or deletion occurs.
Attacks that exploit this kind of access
生成预签名 URL. It is categorised as a Read tool in the TOS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TOS MCP Server MCP server in PolicyLayer and add a rule for tos_presigned_url: 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 TOS MCP Server. Nothing to install.
tos_presigned_url 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 tos_presigned_url 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 tos_presigned_url. 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.
tos_presigned_url is provided by the TOS MCP Server MCP server (jneless/tos-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 →