Get just the summary and metadata of a conversation
AI agents call get_conversation_summary to retrieve information from Claude Code History MCP 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 existing conversation data without creating, modifying, executing, deleting, or moving financial resources. It is a straightforward Read operation with minimal security impact—an AI agent accessing conversation summaries poses low risk since the data is already stored and accessible through normal means.
From the tool's definition Tool name 'get_conversation_summary' and description 'Get just the summary and metadata of a conversation' indicate a retrieval operation with no modification or execution. The action is read-only, returning only summary data and metadata.
Attacks that exploit this kind of access
Get just the summary and metadata of a conversation. It is categorised as a Read tool in the Claude Code History MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Code History MCP server in PolicyLayer and add a rule for get_conversation_summary: 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 Code History MCP. Nothing to install.
get_conversation_summary 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_summary 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_summary. 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_summary is provided by the Claude Code History MCP server (tim0120/claude-code-history-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 →