dump_chat
AI agents call dump_chat to retrieve information from Mnemosyne MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'dump' in the context of chat systems typically means to export or retrieve data (a read operation) rather than modify or delete it. While the empty description reduces confidence, the sibling tools include clearly destructive operations (delete) and constructive ones (create_graph, create_folder), suggesting this tool falls into the Read category.
From the tool's definition Tool name 'dump_chat' suggests exporting or retrieving chat data. The description is empty, limiting certainty. Based on naming convention, this appears to be a read/export operation without modification or deletion capabilities.
Attacks that exploit this kind of access
dump_chat. It is categorised as a Read tool in the Mnemosyne MCP MCP Server, which means it retrieves data without modifying state.
Register the Mnemosyne MCP server in PolicyLayer and add a rule for dump_chat: 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 Mnemosyne MCP. Nothing to install.
dump_chat 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 dump_chat 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 dump_chat. 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.
dump_chat is provided by the Mnemosyne MCP server (sophia-labs/mnemosyne-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 →