AI agents call talon_getConfig 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 tool retrieves configuration information (paths/directories) without side effects. No data is created, modified, deleted, or executed. The blast radius is minimal—an AI agent obtaining config paths could inform subsequent requests but cannot cause direct harm through this tool alone.
From the tool's definition Tool name 'talon_getConfig' and description 'Get Talon configuration paths' indicate retrieval of configuration metadata without modification or execution. Returns paths to home, logs, and user scripts directories.
Attacks that exploit this kind of access
Get Talon configuration paths (home, logs, user scripts). 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_getConfig: 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_getConfig 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_getConfig 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_getConfig. 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_getConfig 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 →