从 TOS 下载对象
AI agents call tos_get_object 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.
This tool retrieves/downloads objects from TOS storage. It performs a read-only operation without modifying, deleting, or executing code. The description explicitly indicates data retrieval ('download'). While exposure of this tool could enable unauthorized data access if credentials are compromised, the tool itself performs no destructive or state-changing operations. This is a standard Read category operation.
From the tool's definition Tool name 'tos_get_object' and description '从 TOS 下载对象' (download object from TOS) indicate retrieval of data from object storage with no side effects.
Attacks that exploit this kind of access
从 TOS 下载对象. 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_get_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 TOS MCP Server. Nothing to install.
tos_get_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 tos_get_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 tos_get_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.
tos_get_object 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 →