get_tool_calls
AI agents call get_tool_calls to retrieve information from Memory MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming convention 'get_*' combined with the memory server's stated purpose of retrieving and searching conversation history suggests this retrieves historical tool invocation records. No modification, deletion, execution, or financial operation is implied.
From the tool's definition Tool name 'get_tool_calls' indicates a retrieval operation with no side effects. The tool name pattern is consistent with query/fetch semantics on a memory server that 'Provides persistent cross-session memory and full-text search'.
Attacks that exploit this kind of access
get_tool_calls. It is categorised as a Read tool in the Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for get_tool_calls: 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 Memory MCP. Nothing to install.
get_tool_calls 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_tool_calls 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_tool_calls. 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_tool_calls is provided by the Memory MCP server (nerdyaustin/memory_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_tool_calls is one line of Memory's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →