Get a structured summary of a conversation session. Provide either a session ID or project name (returns most recent session).
AI agents call get_session_summary to retrieve information from ClaudeHistoryMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves existing conversation history data. It has no side effects, does not modify any data, does not execute external operations, and does not perform irreversible actions. The blast radius of misuse is minimal—an agent could access unwanted historical conversations, but this is a confidentiality concern rather than a capability risk. Classification as Read is appropriate.
From the tool's definition Tool retrieves a structured summary of a conversation session based on provided session ID or project name. The description indicates a read-only operation that returns historical data without modification, deletion, or external effect.
Documented attack patterns abuse exactly the kind of access get_session_summary gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClaudeHistoryMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_session_summary:
{
"version": "1",
"default": "deny",
"tools": {
"get_session_summary": {}
}
}get_session_summary is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a structured summary of a conversation session. Provide either a session ID or project name (returns most recent session). It is categorised as a Read tool in the ClaudeHistoryMCP MCP Server, which means it retrieves data without modifying state.
Register the ClaudeHistory MCP server in PolicyLayer and add a rule for get_session_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 ClaudeHistoryMCP. Nothing to install.
get_session_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_session_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_session_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_session_summary is provided by the ClaudeHistory MCP server (jhammant/claudehistorymcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ClaudeHistoryMCP, 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.
9 ClaudeHistoryMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.