AI agents call read_graph to retrieve information from MCP Memory LibSQL without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation to retrieve entities and their relationships from the graph. There is no creation, modification, deletion, or execution of code. The blast radius is minimal—an agent can only retrieve information that already exists in the memory system. No side effects or irreversible actions are possible.
From the tool's definition Tool name is 'read_graph' and description states 'Get recent entities and their relations' — both indicate retrieval of data without modification.
Documented attack patterns abuse exactly the kind of access read_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Memory LibSQL, and nothing reaches the server without passing your rules. This is the rule we recommend for read_graph:
{
"version": "1",
"default": "deny",
"tools": {
"read_graph": {}
}
}read_graph 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.
Get recent entities and their relations. It is categorised as a Read tool in the MCP Memory LibSQL MCP Server, which means it retrieves data without modifying state.
Register the MCP Memory LibSQL MCP server in PolicyLayer and add a rule for read_graph: 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 Memory LibSQL. Nothing to install.
read_graph 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 read_graph 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 read_graph. 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.
read_graph is provided by the MCP Memory LibSQL MCP server (joleyline/mcp-memory-libsql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Memory LibSQL, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Memory LibSQL tools catalogued and risk-classified — across an index of 43,000+ MCP servers.