Lists all log files in $XDG_RUNTIME_DIR/log. Use this FIRST when user says
AI agents call list_log_files to retrieve information from Log MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
list_log_files performs a directory listing to enumerate log files. This is a pure read operation with no side effects, no code execution, and no data modification. It accesses logs in a standard runtime directory ($XDG_RUNTIME_DIR/log), a typical use case for debugging. The only risk is information disclosure of log file names, which is low severity since logs are typically readable by the application user.
From the tool's definition Tool description states 'Lists all log files' — a retrieval operation with no modification or execution. The server is designed for 'inspect and analyze' log files, and sibling tools include 'read_log_paginated', 'search_log_file', and 'tail_log', all…
Attacks that exploit this kind of access
Lists all log files in $XDG_RUNTIME_DIR/log. Use this FIRST when user says. It is categorised as a Read tool in the Log MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Log MCP Server MCP server in PolicyLayer and add a rule for list_log_files: 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 Log MCP Server. Nothing to install.
list_log_files 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 list_log_files 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 list_log_files. 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.
list_log_files is provided by the Log MCP Server MCP server (thhart/log-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 →