Get full transcript and details of a specific conversation session
AI agents call get_conversation_details to retrieve information from Claude Viewer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries conversation history data—a classic Read operation. However, severity is rated 'high' rather than 'low' because the data being retrieved (full conversation transcripts) likely contains sensitive information including user prompts, API keys, credentials, personal details, and proprietary code that could be exposed across all users on a machine.
From the tool's definition Tool name 'get_conversation_details' and description 'Get full transcript and details of a specific conversation session' indicate retrieval of existing data with no modification or deletion capability.
Attacks that exploit this kind of access
Get full transcript and details of a specific conversation session. It is categorised as a Read tool in the Claude Viewer MCP Server, which means it retrieves data without modifying state.
Register the Claude Viewer MCP server in PolicyLayer and add a rule for get_conversation_details: 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 Claude Viewer. Nothing to install.
get_conversation_details 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_conversation_details 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_conversation_details. 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_conversation_details is provided by the Claude Viewer MCP server (maxturazzini/claude-viewer). 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 →