Zero-LLM repository search using rg when available. Returns bounded file/line matches inside SANDBOX_ROOT.
AI agents call search to retrieve information from MCP Codex Worker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data (searching repository files for matches) with no side effects. It performs a search operation constrained to SANDBOX_ROOT, which is characteristic of Read category tools. The use of 'rg' (ripgrep) for pattern matching confirms it is a passive search utility.
From the tool's definition Tool description states "repository search using rg" and "Returns bounded file/line matches". The name "search" and description indicate read-only querying of repository contents without modification or execution.
Attacks that exploit this kind of access
Zero-LLM repository search using rg when available. Returns bounded file/line matches inside SANDBOX_ROOT. It is categorised as a Read tool in the MCP Codex Worker MCP Server, which means it retrieves data without modifying state.
Register the MCP Codex Worker MCP server in PolicyLayer and add a rule for search: 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 Codex Worker. Nothing to install.
search 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 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. 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 is provided by the MCP Codex Worker MCP server (sorryorc/mcp-codex-worker). 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 →