Search project memory by query string and optional type filters.
AI agents call search_project_memory to retrieve information from MEMGRAPH-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries stored project memory data without any side effects. It does not create, modify, delete, or execute operations—it only searches and returns results. This is a typical Read category tool with minimal risk if misused by an AI agent, as the worst outcome would be retrieving irrelevant or sensitive information already stored in the system.
From the tool's definition The tool description explicitly states 'Search project memory by query string and optional type filters', which indicates a query-based retrieval operation.
Attacks that exploit this kind of access
Search project memory by query string and optional type filters. It is categorised as a Read tool in the MEMGRAPH-MCP MCP Server, which means it retrieves data without modifying state.
Register the MEMGRAPH- MCP server in PolicyLayer and add a rule for search_project_memory: 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 MEMGRAPH-MCP. Nothing to install.
search_project_memory 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 search_project_memory 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 search_project_memory. 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.
search_project_memory is provided by the MEMGRAPH- MCP server (mikeb317/memgraph-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 →