AI agents call search_history 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 search/query operation that retrieves and filters existing data from saved history sessions. It has no side effects, does not modify or delete data, and does not execute external operations. The most severe action is reading traffic metadata, which poses minimal risk even if misused by an agent.
From the tool's definition Tool description explicitly states it 'Search[es] across all saved history sessions' and 'Returns matching requests' — pure retrieval with no modification. Companion tool get_history_detail is separately invoked for deeper inspection.
Attacks that exploit this kind of access
Search across all saved history sessions for requests matching the given filters. Returns matching requests with their session name. Use get_history_detail for full details. 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 search_history: 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.
search_history 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 search_history 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 search_history. 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.
search_history 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 →