AI agents call cross_project_share 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.
This tool retrieves and analyzes search result metadata (cross-project contamination detection) without modifying, deleting, or executing anything. It serves a diagnostic/reporting function for code search quality. The most severe action is reading and comparing data across projects, which is a Read-category operation with minimal blast radius if misused.
From the tool's definition Tool description states it 'share of results' and 'detects' — indicating data retrieval and analysis only. No modification, deletion, or execution described.
Attacks that exploit this kind of access
Per-user-per-anchor-project share of results that came from OTHER projects in the same group. Detects noisy cross-project search. 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 cross_project_share: 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.
cross_project_share 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 cross_project_share 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 cross_project_share. 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.
cross_project_share 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 →