Read-only analysis: read the given files (inside SANDBOX_ROOT) and answer in a single cheap-gateway call. Does NOT start Claude Code and does NOT modify any file. Use for summarize/explain/classify; use start for anything that edits or runs.
AI agents call analyze 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 performs only data retrieval and analysis operations. It reads files to answer questions via a single API call, with no capability to modify, delete, execute, or create resources. The explicit prohibition on file modification and the constraint that it does not start code execution confirms this is a Read category tool with minimal risk.
From the tool's definition Tool description explicitly states 'Read-only analysis: read the given files' and 'Does NOT modify any file'. The tool is limited to reading and analyzing files within SANDBOX_ROOT without side effects.
Attacks that exploit this kind of access
Read-only analysis: read the given files (inside SANDBOX_ROOT) and answer in a single cheap-gateway call. Does NOT start Claude Code and does NOT modify any file. Use for summarize/explain/classify; use start for anything that edits or runs. 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 analyze: 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.
analyze 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 analyze 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 analyze. 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.
analyze 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 →