Add MCP servers to a tenant
AI agents use add_servers_to_tenant to create or update resources in Pointsyeah — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pointsyeah environment.
This tool creates or modifies tenant configuration by adding MCP servers. It is a reversible Write operation (servers can typically be removed), but carries high severity due to the potential security implications of adding servers to a tenant—an attacker could add malicious or unauthorized MCP servers that grant access to unintended resources or capabilities. The blast radius is significant in a multi-tenant system.
From the tool's definition Tool name 'add_servers_to_tenant' and description 'Add MCP servers to a tenant' indicate creating/modifying configuration that adds servers to a tenant.
Attacks that exploit this kind of access
Add MCP servers to a tenant. It is categorised as a Write tool in the Pointsyeah MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pointsyeah MCP server in PolicyLayer and add a rule for add_servers_to_tenant: 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 Pointsyeah. Nothing to install.
add_servers_to_tenant is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_servers_to_tenant 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 add_servers_to_tenant. 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.
add_servers_to_tenant is provided by the Pointsyeah MCP server (slack-workspace-mcp-server). 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 →