MCP server: get_episodes and delete_episode query the wrong graph on FalkorDB (bypass per-group routing)

Not specified by the original author.

[RemanenetSpy (commenter)]: The root cause is storing mutable tenant state on the shared driver (self.driver = self.driver.clone(database=group_id)). In an async MCP runtime, concurrent tool calls create a race condition where read tools query the database of whichever group executed last. The structural fix is replacing mutable driver rebinding with Stateless Per-Request Graph Execution: ```python from typing import Optional, Dict, Any from falkordb import FalkorDB, Graph class MultiTenantGraphitiDriver: def init(self, client: FalkorDB, defaultgroup: str = "default"): self.client = client self.defaultgroup = defaultgroup def getgraph(self, groupid: Optional[str] = None) -> Graph: """Stateless resolution: returns graph handle without mutating shared state.""" targetgroup = groupid or self.defaultgro

Context: GitHub issue getzep/graphiti#1651 (closed, 11 comments): ## Bug description On FalkorDB every group_id is a separate graph (multi-tenant), but the MCP server's get_episodes and delete_episode tools query whatever graph the shared driver happens to be bound to , default_db at startup, or the graph of the last-written group after any add_episode (which rebinds the driver via self.driver = self.driver.clone(database=group_id)). Neither tool routes to the graph of the requested group, so on FalkorDB they operate on the wrong graph and report data as missing that demonstrably exists. This is distinct from #1161 / #1325 (single-group routi

GitHub issue getzep/graphiti#1651 (closed, 11 comments): ## Bug description On FalkorDB every group_id is a separate graph (multi-tenant), but the MCP server's get_episodes and delete_episode tools query whatever graph the shared driver happens to be bound to , default_db at startup, or the graph of the last-written group after any add_episode (which rebinds the driver via self.driver = self.driver.clone(database=group_id)). Neither tool routes to the graph of the requested group, so on FalkorDB they operate on the wrong graph and report data as missing that demonstrably exists. This is distinct from #1161 / #1325 (single-group routi Verified answer: [RemanenetSpy (commenter)]: The root cause is storing mutable tenant state on the shared driver (self.driver = self.driver.clone(database=group_id)). In an async MCP runtime, concurrent tool calls create a race condition where read tools query the database of whichever group executed last. The structural fix is replacing mutable driver rebinding with Stateless Per-Request Graph Execution: ```python from typing import Optional, Dict, Any from falkordb import FalkorDB, Graph class MultiTenantGraphitiDriver: def init(self, client: FalkorDB, defaultgroup: str = "default"): self.client = client self.defaultgroup = defaultgroup def getgraph(self, groupid: Optional[str] = None) -> Graph: """Stateless resolution: returns graph handle without mutating shared state.""" targetgroup = groupid or self.defaultgro Source: https://github.com/getzep/graphiti/issues/1651