AI agents use update_conference to create or update resources in Confd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Confd environment.
The tool creates or modifies data reversibly (the definition of Write). It updates conference records without permanently deleting them, so it is not Destructive. It does not execute arbitrary code or commands, so it is not Execute. The moderate severity reflects that a misused update could corrupt conference data, but the effect is reversible (data can be corrected or restored), preventing a higher rating.
From the tool's definition Tool name is 'update_conference' and description states 'Update an existing conference by ID. Only include fields you want to change.' — this modifies existing data.
Attacks that exploit this kind of access
Update an existing conference by ID. Only include fields you want to change. It is categorised as a Write tool in the Confd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Confd MCP server in PolicyLayer and add a rule for update_conference: 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 Confd. Nothing to install.
update_conference 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 update_conference 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 update_conference. 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.
update_conference is provided by the Confd MCP server (mytours/confd-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 →