AI agents call seoagent_projects_list to retrieve information from Seoagent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents existing project/domain data from the SEO toolkit's tracking system. It has no side effects, performs no modifications, executes no commands, and carries minimal risk even if misused by an AI agent. The worst outcome would be information disclosure of already-tracked domains, which is low severity.
From the tool's definition Tool name contains 'list' and description states 'List all tracked SEOAgent projects/domains' — a straightforward query operation that retrieves data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
List all tracked SEOAgent projects/domains. It is categorised as a Read tool in the Seoagent MCP Server, which means it retrieves data without modifying state.
Register the Seoagent MCP server in PolicyLayer and add a rule for seoagent_projects_list: 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 Seoagent. Nothing to install.
seoagent_projects_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the seoagent_projects_list 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 seoagent_projects_list. 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.
seoagent_projects_list is provided by the Seoagent MCP server (yagomp/seoagent). 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 →