Set a short status summary so other peers can discover what this Codex session is working on.
AI agents use set_summary to create or update resources in Codex Peers MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codex Peers MCP environment.
This tool modifies peer metadata (a status summary) on a shared broker to enable peer discovery. It is reversible (the summary can be updated or cleared), has no destructive or financial implications, and does not execute code or retrieve sensitive data.
From the tool's definition Tool description states 'Set a short status summary' — this is a write operation that creates or modifies a status field visible to other peers. The verb 'set' indicates data modification.
Attacks that exploit this kind of access
Set a short status summary so other peers can discover what this Codex session is working on. It is categorised as a Write tool in the Codex Peers MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codex Peers MCP server in PolicyLayer and add a rule for set_summary: 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 Codex Peers MCP. Nothing to install.
set_summary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_summary 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 set_summary. 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.
set_summary is provided by the Codex Peers MCP server (jscianna/codex-peers-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 →