Allow or deny a pending permission_request from a peer. Only valid if a request with this request_id is live.
AI agents invoke respond_to_permission to trigger actions in Claude Mesh. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool approves or denies permission requests from other Claude instances in the mesh network. The act of granting permission can allow peer agents to perform subsequent actions (potentially destructive, financial, or otherwise). It is an authorization gate whose effect depends on arguments (allow vs.
From the tool's definition 'Allow or deny a pending permission_request from a peer' — this triggers an authorization decision that grants or revokes execution rights for a peer Claude instance
Documented attack patterns abuse exactly the kind of access respond_to_permission gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Mesh, and nothing reaches the server without passing your rules. This is the rule we recommend for respond_to_permission:
{
"version": "1",
"default": "deny",
"tools": {
"respond_to_permission": {
"limits": [
{
"counter": "respond_to_permission_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}respond_to_permission stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Allow or deny a pending permission_request from a peer. Only valid if a request with this request_id is live. It is categorised as a Execute tool in the Claude Mesh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Mesh MCP server in PolicyLayer and add a rule for respond_to_permission: 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 Mesh. Nothing to install.
respond_to_permission is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the respond_to_permission 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 respond_to_permission. 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.
respond_to_permission is provided by the Claude Mesh MCP server (pouriamrt/claude-mesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Mesh, 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 Mesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.