Get all Viva Engage communities/groups the user is a member of in their home network
AI agents call get_communities to retrieve information from Mcp Viva Engage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that lists communities the authenticated user belongs to. It retrieves information without creating, modifying, deleting, or executing any operations. The low severity reflects minimal blast radius: exposure of community membership lists poses informational risk but no direct operational harm.
From the tool's definition Tool name is 'get_communities' and description states 'Get all Viva Engage communities/groups the user is a member of' — purely retrieves/queries data with no side effects.
Attacks that exploit this kind of access
Get all Viva Engage communities/groups the user is a member of in their home network. It is categorised as a Read tool in the Mcp Viva Engage MCP Server, which means it retrieves data without modifying state.
Register the Mcp Viva Engage MCP server in PolicyLayer and add a rule for get_communities: 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 Mcp Viva Engage. Nothing to install.
get_communities 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_communities 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_communities. 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_communities is provided by the Mcp Viva Engage MCP server (pranav4186/mcp-viva-engage). 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 →