search_project
AI agents call search_project to retrieve information from Unreal Project without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on context, 'search_project' appears to be a read-only query tool for searching an indexed SQLite database of Unreal Engine project information. All sibling tools perform retrieval without modification. The server's stated purpose is to expose tools for querying structural and config info, with no write or execute capabilities mentioned. No side effects are expected from a search operation.
From the tool's definition Tool name 'search_project' combined with server description indicating tools 'query structural and config info' and sibling tools like 'find_asset_references', 'find_data_table_schema', 'find_log_sites', 'find_project_callees', 'find_project_callers',…
Attacks that exploit this kind of access
search_project. It is categorised as a Read tool in the Unreal Project MCP Server, which means it retrieves data without modifying state.
Register the Unreal Project MCP server in PolicyLayer and add a rule for search_project: 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 Unreal Project. Nothing to install.
search_project 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_project 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_project. 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_project is provided by the Unreal Project MCP server (tumourlove/deprecated-unreal-project-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 →