AI agents call talon_getScope to retrieve information from Talon MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that surfaces runtime state and configuration details from the Talon framework. It has no side effects, does not execute arbitrary code, and does not modify any data. The low severity reflects minimal blast radius—an AI agent misusing this tool would only retrieve unwanted state information, not cause system damage or data loss.
From the tool's definition Tool retrieves current Talon scope information including mode, active app, window title, speech status, tags, and contexts. Uses 'Get' verb and 'keys parameter to filter results' indicates querying/fetching behavior with no modification or side effects.
Attacks that exploit this kind of access
Get current Talon scope: mode (command/dictation), active app, window title, speech status, active tags, and active contexts. Use keys parameter to filter results. It is categorised as a Read tool in the Talon MCP MCP Server, which means it retrieves data without modifying state.
Register the Talon MCP server in PolicyLayer and add a rule for talon_getScope: 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 Talon MCP. Nothing to install.
talon_getScope 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 talon_getScope 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 talon_getScope. 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.
talon_getScope is provided by the Talon MCP server (trillium/talon_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 →