List other Claude Code instances running on this machine. Returns their ID, working directory, git repo, and summary.
AI agents call list_peers to retrieve information from Claude Peers 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 information about active peer instances without modifying, executing, or deleting anything. It has no side effects beyond returning read-only metadata about running processes. The blast radius of misuse is minimal—an agent could learn about other projects or directories but cannot modify them or execute code.
From the tool's definition Tool name is 'list_peers' and description states it 'List[s] other Claude Code instances running on this machine. Returns their ID, working directory, git repo, and summary.' The verb 'List' and 'Returns' indicate data retrieval only.
Documented attack patterns abuse exactly the kind of access list_peers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Peers, and nothing reaches the server without passing your rules. This is the rule we recommend for list_peers:
{
"version": "1",
"default": "deny",
"tools": {
"list_peers": {}
}
}list_peers is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List other Claude Code instances running on this machine. Returns their ID, working directory, git repo, and summary. It is categorised as a Read tool in the Claude Peers MCP Server, which means it retrieves data without modifying state.
Register the Claude Peers MCP server in PolicyLayer and add a rule for list_peers: 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 Claude Peers. Nothing to install.
list_peers 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_peers 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_peers. 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_peers is provided by the Claude Peers MCP server (louislva/claude-peers-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Peers, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Claude Peers tools catalogued and risk-classified — across an index of 43,000+ MCP servers.