Return a compact summary of the latest calculations in this session.
AI agents call history-summary to retrieve information from Example Mcp Server Sse 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 session history data, presenting it in a summarized format. There is no indication of data modification, deletion, code execution, or financial operations. It is a pure read operation with minimal security risk.
From the tool's definition Tool name 'history-summary' and description 'Return a compact summary of the latest calculations in this session' indicate retrieval of historical data without modification or side effects.
Attacks that exploit this kind of access
Return a compact summary of the latest calculations in this session. It is categorised as a Read tool in the Example Mcp Server Sse MCP Server, which means it retrieves data without modifying state.
Register the Example Mcp Server Sse MCP server in PolicyLayer and add a rule for history-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 Example Mcp Server Sse. Nothing to install.
history-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 history-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 history-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.
history-summary is provided by the Example Mcp Server Sse MCP server (yigitkonur/example-mcp-sse). 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 →