AI agents call get_computers 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.
The 'get_' prefix and context within an AD querying service indicates this retrieves computer data without modification. However, severity is medium (not low) because Active Directory computer objects can contain sensitive operational information (hostnames, IP addresses, OS versions, group memberships, service account details) that could inform further attacks, even though the tool itself is read-only.
From the tool's definition Tool name is 'get_computers' which follows the 'get_*' pattern indicating data retrieval. Server context shows this MCP exposes Active Directory data as 'queryable tools' for LLMs.
Attacks that exploit this kind of access
get_computers. 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_computers: 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_computers 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_computers 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_computers. 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_computers 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 →