AI agents call get_site_links 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 retrieves existing Active Directory site link metadata (cost, replication intervals) for assessment purposes. No data is created, modified, deleted, or executed—it simply queries and returns information. The blast radius of misuse is limited to potential information disclosure about AD replication topology, which is low severity for an on-premises assessment context.
From the tool's definition Tool name 'get_site_links' and description 'Return all site links with cost, replication interval' indicate data retrieval with no modification or side effects. The verb 'get' and 'return' confirm read-only querying of Active Directory site link configuration.
Attacks that exploit this kind of access
Return all site links with cost, replication interval,. 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_site_links: 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_site_links 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_site_links 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_site_links. 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_site_links 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 →