AI agents use switch_conversation to create or update resources in Membase MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Membase MCP Server environment.
The tool appears to modify which conversation is active or selected within a persistent memory system. While not creating or deleting data (not Destructive), it changes application state and context. This is a Write operation—reversible state modification.
From the tool's definition Tool name 'switch_conversation' combined with sibling tools 'get_conversation_id', 'get_messages', and 'save_message' indicates state management operations.
Documented attack patterns abuse exactly the kind of access switch_conversation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Membase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for switch_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"switch_conversation": {
"limits": [
{
"counter": "switch_conversation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} switch_conversation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
switch_conversation. It is categorised as a Write tool in the Membase MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Membase MCP Server MCP server in PolicyLayer and add a rule for switch_conversation: 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 Membase MCP Server. Nothing to install.
switch_conversation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the switch_conversation 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 switch_conversation. 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.
switch_conversation is provided by the Membase MCP Server MCP server (unibaseio/membase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Membase 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.
4 Membase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.