AI agents call get_bundle 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.
get_bundle is a retrieval-only operation that fetches a pre-compiled context bundle without modifying any underlying state. This is a standard Read operation typical of memory/context systems. The 'low' severity reflects that retrieved metadata about a project poses minimal risk even if misused by an agent, as it does not enable code execution, data deletion, or financial transactions.
From the tool's definition Tool description explicitly states 'Get' (retrieves data) and includes only informational content: 'description, tech stack, recent sessions, and key concepts.' No modification, deletion, execution, or financial operations are mentioned.
Attacks that exploit this kind of access
Get pre-compiled context bundle for a specific project. Includes description, tech stack, recent sessions, and key concepts. 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 get_bundle: 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.
get_bundle 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 get_bundle 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 get_bundle. 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.
get_bundle 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 →