AI agents invoke subscribe_to_channel to trigger actions in Spline. 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.
Subscribing to a WebSocket channel initiates an ongoing external connection/operation that triggers real-time data streaming. This goes beyond a simple read since it establishes a persistent connection and registers a listener for continuous updates, qualifying as an external operation execution. The blast radius is medium as misuse could result in unintended persistent connections or data exposure.
From the tool's definition Subscribe to a WebSocket channel for real-time updates
Attacks that exploit this kind of access
Subscribe to a WebSocket channel for real-time updates. It is categorised as a Execute tool in the Spline MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spline MCP server in PolicyLayer and add a rule for subscribe_to_channel: 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 Spline. Nothing to install.
subscribe_to_channel 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 subscribe_to_channel 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 subscribe_to_channel. 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.
subscribe_to_channel is provided by the Spline MCP server (lesleslie/spline-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 →