Search command history by keyword.
AI agents call search_commands_tool to retrieve information from Mcp Commands 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 search operation over historical command data. It does not create, modify, delete, or execute commands; it only queries and retrieves information. The blast radius of misuse is minimal — an attacker could view command history but not alter or execute commands. This is a classic Read category operation.
From the tool's definition Tool description states 'Search command history by keyword' — a query operation with no modification or deletion capability. The server manages command usage history in PostgreSQL, and this tool retrieves/searches existing records without side effects.
Attacks that exploit this kind of access
Search command history by keyword. It is categorised as a Read tool in the Mcp Commands MCP Server, which means it retrieves data without modifying state.
Register the Mcp Commands MCP server in PolicyLayer and add a rule for search_commands_tool: 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 Mcp Commands. Nothing to install.
search_commands_tool 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 search_commands_tool 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 search_commands_tool. 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.
search_commands_tool is provided by the Mcp Commands MCP server (puemmth/mcp-commands). 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 →