AI agents call get_objects_by_name to retrieve information from MITRE ATT&CK MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve objects from the MITRE ATT&CK database by name matching. This is a read-only query operation with no destructive, financial, or code execution capabilities. The blast radius is minimal—incorrect usage returns irrelevant data rather than causing harm.
From the tool's definition Tool name 'get_objects_by_name' indicates a query/retrieval operation. The empty description limits direct evidence, but the naming pattern (get_*) and context within MITRE ATT&CK (a threat intelligence knowledge base) suggest data retrieval without side…
Documented attack patterns abuse exactly the kind of access get_objects_by_name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MITRE ATT&CK MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_objects_by_name:
{
"version": "1",
"default": "deny",
"tools": {
"get_objects_by_name": {}
}
}get_objects_by_name is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_objects_by_name. It is categorised as a Read tool in the MITRE ATT&CK MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MITRE ATT&CK MCP Server MCP server in PolicyLayer and add a rule for get_objects_by_name: 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 MITRE ATT&CK MCP Server. Nothing to install.
get_objects_by_name 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_objects_by_name 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_objects_by_name. 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_objects_by_name is provided by the MITRE ATT&CK MCP Server MCP server (stoyky/mitre-attack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 55 MITRE ATT&CK MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
55 MITRE ATT&CK MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.