Create or update an organization by source identifier. If an organization with the given source exists, it is updated. If not, a new one is created. Source is required. Will be rejected if the existing record has do_not_import set.
AI agents use upsert_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.
This tool creates new organization records or modifies existing ones based on source identifier. These are reversible write operations (the data can be deleted or re-edited later), not destructive. While it affects organizational data, the impact is scoped to a single organization record and the changes can be undone.
From the tool's definition Tool description explicitly states 'Create or update an organization' — core write operations that modify data reversibly. The upsert pattern (create if absent, update if present) is a standard write operation.
Attacks that exploit this kind of access
Create or update an organization by source identifier. If an organization with the given source exists, it is updated. If not, a new one is created. Source is required. Will be rejected if the existing record has do_not_import 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 upsert_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.
upsert_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 upsert_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 upsert_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.
upsert_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 →