Update site configuration
AI agents use update_site to create or update resources in Fastly NGWAF MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fastly NGWAF MCP Server environment.
This tool modifies site configuration within a WAF system, which is a reversible write operation affecting security-critical settings. While the changes are not permanent deletions (ruling out Destructive), they could impact multiple aspects of site security and traffic. Severity is high because misconfigured WAF rules could expose applications to attacks or block legitimate traffic.
From the tool's definition Tool name is 'update_site' with description 'Update site configuration'. The verb 'update' indicates modification of existing data (site configuration).
Attacks that exploit this kind of access
Update site configuration. It is categorised as a Write tool in the Fastly NGWAF MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fastly NGWAF MCP Server MCP server in PolicyLayer and add a rule for update_site: 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 Fastly NGWAF MCP Server. Nothing to install.
update_site 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_site 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_site. 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_site is provided by the Fastly NGWAF MCP Server MCP server (purpleax/fastlymcp). 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 →