Get the complete HAR entry for a specific request from history. Returns full request headers, body, response headers, response body, and timing. Use the request ID from search_history or get_history_requests.
AI agents call get_history_detail to retrieve information from Proxypin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only tool that retrieves detailed information about captured HTTP traffic. However, severity is elevated to 'high' because the retrieved data can include sensitive information (authentication tokens, cookies, POST body data, API responses, etc.) that could be misused by a compromised AI agent. The tool itself performs no side effects, but the data it exposes has high value for attackers.
From the tool's definition Tool returns complete HTTP request/response data including headers, body, and timing from captured traffic history. It 'Get(s) the complete HAR entry for a specific request' and 'Returns full request headers, body, response headers, response body'.
Attacks that exploit this kind of access
Get the complete HAR entry for a specific request from history. Returns full request headers, body, response headers, response body, and timing. Use the request ID from search_history or get_history_requests. It is categorised as a Read tool in the Proxypin MCP Server, which means it retrieves data without modifying state.
Register the Proxypin MCP server in PolicyLayer and add a rule for get_history_detail: 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 Proxypin. Nothing to install.
get_history_detail 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_history_detail 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_history_detail. 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_history_detail is provided by the Proxypin MCP server (k186/proxypin-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 →