Search your prompt history by keyword.
AI agents call history_search to retrieve information from RespCode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches and retrieves existing prompt history data. Searching is a read-only operation that does not create, modify, delete, or execute any code. While it accesses user history (which could contain sensitive information in principle), the tool itself poses minimal risk as it merely retrieves data without persistence-altering effects.
From the tool's definition Tool name 'history_search' and description 'Search your prompt history by keyword' indicate a retrieval operation with no side effects. This is a query/search function that accesses historical data without modification.
Attacks that exploit this kind of access
Search your prompt history by keyword. It is categorised as a Read tool in the RespCode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RespCode MCP Server MCP server in PolicyLayer and add a rule for history_search: 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 RespCode MCP Server. Nothing to install.
history_search 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_search 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_search. 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_search is provided by the RespCode MCP Server MCP server (respcodeai/respcode-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 →