AI agents call search_changes to retrieve information from Paparats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search through version control or change history to retrieve information. This is a read-only operation with no side effects—it queries data without creating, modifying, deleting, or executing anything. The absence of a detailed description lowers confidence slightly, but the naming pattern and server context support classification as a read operation.
From the tool's definition Tool name 'search_changes' indicates querying/retrieving change history or diffs. The description is empty, but context from sibling tools (arch_list, arch_context, search implies retrieval operations) and the server's purpose (semantic code search) strongly…
Attacks that exploit this kind of access
search_changes. It is categorised as a Read tool in the Paparats MCP Server, which means it retrieves data without modifying state.
Register the Paparats MCP server in PolicyLayer and add a rule for search_changes: 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 Paparats. Nothing to install.
search_changes 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_changes 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_changes. 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_changes is provided by the Paparats MCP server (@paparats/cli). 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 →