AI agents use set-topic-permission to create or update resources in Rabbitmq — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rabbitmq environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
read | string | Yes | |
user | string | Yes | |
vhost | string | Yes | |
write | string | Yes | |
exchange | string | Yes |
Parameters from the server's own tool schema.
This tool modifies security-related configuration (topic permissions) but the changes are reversible—permissions can be updated or revoked. It does not execute arbitrary code, delete data, move money, or make permanent destructive changes. The blast radius is contained to permission scope changes for a specific user/vhost combination.
From the tool's definition Tool name 'set-topic-permission' and description 'Set topic permissions for a user in a vhost' indicate modification of access control configuration. This creates or modifies permission rules that govern user access to RabbitMQ topics.
Attacks that exploit this kind of access
Set topic permissions for a user in a vhost. It is categorised as a Write tool in the Rabbitmq MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
set-topic-permission accepts 5 parameters: read, user, vhost, write, exchange. Required: read, user, vhost, write, exchange. The full parameter table on this page comes from the server's own tool schema.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for set-topic-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 Rabbitmq. Nothing to install.
set-topic-permission 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-topic-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 set-topic-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.
set-topic-permission is provided by the Rabbitmq MCP server (rabbitmq-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 →