AI agents use update_organization 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 (organization records) in a reversible manner. While it changes persistent data, updates are not destructive—the original data can be recovered or the change can be undone by updating again. This places it in the Write category.
From the tool's definition Tool description explicitly states 'Update an existing organization by ID' and 'Only include fields you want to change', indicating reversible modification of organization records.
Attacks that exploit this kind of access
Update an existing organization by ID. Only include fields you want to change. Works even if do_not_import is set. 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_organization: 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_organization 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_organization 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_organization. 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_organization 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 →