AI agents call talon_getLogsQuery 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 performs a read-only operation on existing logs using a text search filter. It retrieves and queries log data without creating, modifying, deleting, or executing any actions. The log-filtering pattern is consistent with other sibling tools (talon_getRecentLogs, talon_getLogsRegex) that are clearly informational. No side effects or state changes result from filtering logs.
From the tool's definition Tool name 'getLogsQuery' and description 'Filter Talon logs by text search query' indicate log retrieval and filtering operations with no data modification or execution capabilities.
Attacks that exploit this kind of access
Filter Talon logs by text search query. 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_getLogsQuery: 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_getLogsQuery 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_getLogsQuery 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_getLogsQuery. 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_getLogsQuery 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 →