Update an existing B2B company
AI agents use update_company to create or update resources in Shopify Graphql — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shopify Graphql environment.
The tool modifies company data in a Shopify store but does not delete it (reversible) and does not involve financial transactions directly. Within a B2B context, company updates could affect business relationships and access controls, warranting medium severity due to potential impact on store operations, but the effect is not destructive or financially consequential in itself.
From the tool's definition Tool name and description both indicate modification: 'Update an existing B2B company'. This aligns with the Write category definition of 'creates or modifies data reversibly'.
Attacks that exploit this kind of access
Update an existing B2B company. It is categorised as a Write tool in the Shopify Graphql MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for update_company: 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 Shopify Graphql. Nothing to install.
update_company 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_company 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_company. 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_company is provided by the Shopify Graphql MCP server (uvu-store/shopify-graphql-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 →