AI agents call cross_project_search to retrieve information from Engram 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 tool that retrieves and returns information without modifying, creating, or deleting any data. The grouped results with relevance scores are read-only outputs. No write, execute, destructive, or financial operations are possible with this tool. The blast radius of misuse is minimal since it only exposes information already accessible within projects.
From the tool's definition Tool description states 'Search across ALL projects semantically' and 'finding related work across the entire codebase' — pure retrieval/query operation with no data modification capability mentioned.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search across ALL projects semantically. Groups results by project with relevance scores. Great for finding related work across the entire codebase. It is categorised as a Read tool in the Engram MCP Server, which means it retrieves data without modifying state.
Register the Engram MCP server in PolicyLayer and add a rule for cross_project_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 Engram. Nothing to install.
cross_project_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 cross_project_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 cross_project_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.
cross_project_search is provided by the Engram MCP server (tinydarkforge/engram). 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 →