AI agents call get_entity to retrieve information from Dbrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored information from persistent memory without altering, deleting, or executing anything. It is a straightforward query operation analogous to a GET request or SELECT statement. The blast radius of misuse is minimal — an agent could retrieve facts about entities it may not be authorized to access, but no data loss, code execution, or financial impact occurs.
From the tool's definition Tool name is 'get_entity' and description states 'Read an entity and all its facts' — explicitly a read operation with no modification or side effects.
Attacks that exploit this kind of access
Read an entity and all its facts. Use this to get full context about a project, person, system, or event. It is categorised as a Read tool in the Dbrain MCP Server, which means it retrieves data without modifying state.
Register the Dbrain MCP server in PolicyLayer and add a rule for get_entity: 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 Dbrain. Nothing to install.
get_entity 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_entity 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_entity. 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_entity is provided by the Dbrain MCP server (ivncmp/dbrain). 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 →