AI agents call list_code_sources 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.
The 'list' prefix is characteristic of Read operations that query or retrieve data. Given the sibling tools focus on code source management and the name pattern, this tool most likely queries stored code sources without side effects. Confidence is moderate (0.7) because the empty description limits certainty about underlying implementation, though the name strongly implies a Read operation.
From the tool's definition Tool name 'list_code_sources' indicates a listing/retrieval operation. The description is empty, but the name and context (sibling tools include add_code_source, find_code_orphans) suggest this retrieves or enumerates existing code sources without…
Attacks that exploit this kind of access
list_code_sources. 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_code_sources: 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_code_sources 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_code_sources 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_code_sources. 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_code_sources 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 →