Get the current status of all episode processing queues. Shows total pending tasks, active workers, and per-group_id queue details. Use this to monitor background processing after adding memories.
AI agents call get_queue_status to retrieve information from Graphiti Knowledge Graph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries and retrieves monitoring information about background queue state. It has no side effects, makes no modifications to the knowledge graph, executes no code, and causes no data loss. The blast radius of misuse is minimal—an AI agent could at worst read operational metrics, which poses negligible security risk.
From the tool's definition Tool name 'get_queue_status' and description 'Get the current status of all episode processing queues. Shows total pending tasks, active workers, and per-group_id queue details.' — uses action verb 'Get' and explicitly retrieves status information without…
Documented attack patterns abuse exactly the kind of access get_queue_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Graphiti Knowledge Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_queue_status:
{
"version": "1",
"default": "deny",
"tools": {
"get_queue_status": {}
}
} get_queue_status 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 the current status of all episode processing queues. Shows total pending tasks, active workers, and per-group_id queue details. Use this to monitor background processing after adding memories. It is categorised as a Read tool in the Graphiti Knowledge Graph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Graphiti Knowledge Graph MCP Server MCP server in PolicyLayer and add a rule for get_queue_status: 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 Graphiti Knowledge Graph MCP Server. Nothing to install.
get_queue_status 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_queue_status 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_queue_status. 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_queue_status is provided by the Graphiti Knowledge Graph MCP Server MCP server (michabbb/graphiti-mcp-but-working). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Graphiti Knowledge Graph MCP Server, 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.
11 Graphiti Knowledge Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.