forbid_live_stream
AI agents invoke forbid_live_stream to trigger actions in Tencent Cloud Live MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Forbidding a live stream is an operational action that interrupts or blocks an active stream, which is an external operation with real-world impact. It is more severe than a simple write but not necessarily irreversible (streams can typically be re-enabled), so Execute is most appropriate. The empty description lowers confidence, but the name clearly implies stream interruption.
From the tool's definition Tool name 'forbid_live_stream' suggests blocking/interrupting a live stream; description is empty and uninformative.
Attacks that exploit this kind of access
forbid_live_stream. It is categorised as a Execute tool in the Tencent Cloud Live MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tencent Cloud Live MCP Server MCP server in PolicyLayer and add a rule for forbid_live_stream: 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 Tencent Cloud Live MCP Server. Nothing to install.
forbid_live_stream is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the forbid_live_stream 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 forbid_live_stream. 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.
forbid_live_stream is provided by the Tencent Cloud Live MCP Server MCP server (willsygao/tencentcloud-live-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 →