AI agents call list_available_qa_files to retrieve information from SEED MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates available files without creating, modifying, deleting, or executing anything. It is a straightforward informational query, posing minimal risk even if called by an AI agent without proper authorization, as it only discloses what files exist in the system.
From the tool's definition Tool name is 'list_available_qa_files' and description states it 'List[s] available GIINT QA files for ingestion' — a pure query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List available GIINT QA files for ingestion. It is categorised as a Read tool in the SEED MCP MCP Server, which means it retrieves data without modifying state.
Register the SEED MCP server in PolicyLayer and add a rule for list_available_qa_files: 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 SEED MCP. Nothing to install.
list_available_qa_files 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 list_available_qa_files 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 list_available_qa_files. 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.
list_available_qa_files is provided by the SEED MCP server (sancovp/seed-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 →