waf mcp-security policy
Use this command to group rules and enable the primary inspection engines (Signature Detection, Poisoning Attack Protection, and JSON Schema Validation).
config waf mcp-security policy
edit <mcp-security_policy_name>
set signature-detection {enable|disable}
set poisoning-attack-scan {enable|disable}
set json-schema-validation {enable|disable}
config rule-list
edit <rule-list_id>
set rule <rule_name>
next
end
next
end
| <mcp-security_policy_name> |
Enter a unique name for the policy that can be referenced by other parts of the configuration. |
No default.
|
| signature-detection {enable|disable} |
Enable to prevent attacks on the MCP server, such as injection or command execution. FortiWeb evaluates MCP fields including methods, tool names, and argument values for indicators of unsafe behavior. |
disable
|
| poisoning-attack-scan {enable|disable} |
Enable to prevent adversarial attempts to manipulate LLM behavior or steal sensitive information. This scans tool descriptions, tool parameters, and prompt content. |
disable
|
|
json-schema-validation {enable|disable}
|
Enable to ensure each streamed MCP message meets the official specification provided by FortiGuard based on the MCP version. |
disable
|
|
config rule-list
|
|
<rule-list_id>
|
Enter the sequence number of the rule in the rule list.
|
No default.
|
|
rule <rule_name>
|
Select the created MCP Security Rule name.
|
No default.
|
Related topics
waf mcp-security rule
waf mcp-security exception