AI agents call get_groups to retrieve information from LegacyMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Active Directory group data, consistent with the server's stated purpose of enabling assessment via queryable data exposure. The 'get_' prefix and absence of any modification language classify it as a Read operation. Low severity because reading AD group metadata has limited blast radius compared to destructive or financial operations, though access control should still be considered.
From the tool's definition Tool name 'get_groups' with 'get_' prefix indicates data retrieval. No description provided, but context from sibling tools (all prefixed with 'get_' or 'create_snapshot') and server purpose (exposing AD data as queryable tools) suggests this retrieves Active…
Attacks that exploit this kind of access
get_groups. It is categorised as a Read tool in the LegacyMCP MCP Server, which means it retrieves data without modifying state.
Register the Legacy MCP server in PolicyLayer and add a rule for get_groups: 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 LegacyMCP. Nothing to install.
get_groups 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_groups 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_groups. 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_groups is provided by the Legacy MCP server (marco-lelli/legacy-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 →