GRAPH RELATED CONNECTED NETWORK - Search memories and traverse relationships to find connected information. Keywords: graph, related, connected, network, relationships, linked, associated, traverse connections
AI agents call memory_graph_search to retrieve information from MCP AI Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic queries across stored memory records and their relational graph, returning connected information. There are no indications of data creation, modification, deletion, or external execution. The traversal of graph relationships is a read operation that retrieves and presents existing data without side effects.
From the tool's definition Tool description explicitly states it "Search[es] memories and traverse[s] relationships to find connected information" with keywords including "search," "related," "connected," "network," "relationships," "linked," "associated," and "traverse connections."…
Documented attack patterns abuse exactly the kind of access memory_graph_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP AI Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_graph_search:
{
"version": "1",
"default": "deny",
"tools": {
"memory_graph_search": {}
}
}memory_graph_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
GRAPH RELATED CONNECTED NETWORK - Search memories and traverse relationships to find connected information. Keywords: graph, related, connected, network, relationships, linked, associated, traverse connections. It is categorised as a Read tool in the MCP AI Memory MCP Server, which means it retrieves data without modifying state.
Register the MCP AI Memory MCP server in PolicyLayer and add a rule for memory_graph_search: 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 MCP AI Memory. Nothing to install.
memory_graph_search 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 memory_graph_search 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 memory_graph_search. 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.
memory_graph_search is provided by the MCP AI Memory MCP server (scanadi/mcp-ai-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 MCP AI Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 MCP AI Memory tools catalogued and risk-classified — across an index of 42,500+ MCP servers.