Retrieves recent records from the database.
AI agents call get_records to retrieve information from Pg Mnemosyne without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a retrieval/query operation on stored data without side effects. It matches the 'Read' category pattern of fetching or querying data. The severity is low because retrieval operations have minimal blast radius—they cannot modify, delete, or trigger external operations. High confidence due to clear read-only semantics in both name and description.
From the tool's definition Tool name 'get_records' and description 'Retrieves recent records from the database' indicate a query operation with no modification or deletion.
Attacks that exploit this kind of access
Retrieves recent records from the database. It is categorised as a Read tool in the Pg Mnemosyne MCP Server, which means it retrieves data without modifying state.
Register the Pg Mnemosyne MCP server in PolicyLayer and add a rule for get_records: 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 Pg Mnemosyne. Nothing to install.
get_records 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_records 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_records. 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_records is provided by the Pg Mnemosyne MCP server (janadasroor/pg-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 →