Get the user's current graph and document IDs.
AI agents call get_user_location to retrieve information from Mnemosyne 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 returns data (graph and document IDs) with no side effects or mutations. It is a straightforward read operation. The severity is low because the blast radius of exposing user IDs is minimal—these are likely identifiers needed for normal system operation, not sensitive credentials or high-impact data.
From the tool's definition Tool name 'get_user_location' and description 'Get the user's current graph and document IDs' indicate a retrieval operation that returns identifiers without modifying state.
Attacks that exploit this kind of access
Get the user's current graph and document IDs. It is categorised as a Read tool in the Mnemosyne MCP MCP Server, which means it retrieves data without modifying state.
Register the Mnemosyne MCP server in PolicyLayer and add a rule for get_user_location: 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 Mnemosyne MCP. Nothing to install.
get_user_location 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 get_user_location 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 get_user_location. 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.
get_user_location is provided by the Mnemosyne MCP server (sophia-labs/mnemosyne-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 →