get_my_active_conversations
AI agents call get_my_active_conversations to retrieve information from Cluster Execution MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query active conversation state/metadata without modifying or executing operations. This is characteristic of a Read operation. Severity is medium rather than low because in a cluster execution context, querying active conversations could potentially expose sensitive task details, arguments, or communication patterns across distributed nodes if an agent misuses it to gather…
From the tool's definition Tool name 'get_my_active_conversations' suggests querying/retrieving conversation data with no side effects. The server context (cluster execution, task routing) implies this retrieves metadata about active tasks or communications across cluster nodes.
Attacks that exploit this kind of access
get_my_active_conversations. It is categorised as a Read tool in the Cluster Execution MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cluster Execution MCP Server MCP server in PolicyLayer and add a rule for get_my_active_conversations: 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 Cluster Execution MCP Server. Nothing to install.
get_my_active_conversations 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_my_active_conversations 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_my_active_conversations. 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_my_active_conversations is provided by the Cluster Execution MCP Server MCP server (marc-shade/cluster-execution-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →