AI agents call list_upstream_tools to retrieve information from Memex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the description is empty (lowering confidence), the name clearly suggests a retrieval/query operation ('list') that would enumerate upstream tools. This is consistent with the server's purpose as a 'MCP gateway' that needs to catalog available tools. No side effects, modifications, code execution, deletions, or financial implications are implied.
From the tool's definition Tool name 'list_upstream_tools' indicates a read operation that retrieves or queries information about available tools from upstream MCP servers. The 'list' verb and 'upstream' context suggest enumeration without modification.
Attacks that exploit this kind of access
list_upstream_tools. It is categorised as a Read tool in the Memex MCP Server, which means it retrieves data without modifying state.
Register the Memex MCP server in PolicyLayer and add a rule for list_upstream_tools: 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 Memex. Nothing to install.
list_upstream_tools 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_upstream_tools 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_upstream_tools. 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_upstream_tools is provided by the Memex MCP server (queflyhq/memex). 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 →