manage_graph_subscriptions
AI agents use manage_graph_subscriptions to create or update resources in Microsoft 365 Core MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft 365 Core MCP Server environment.
Managing subscriptions involves creating, updating, or deleting webhook subscriptions in Microsoft 365, which modifies system state and configuration. This is Write-category because subscriptions are typically reversible (can be deleted/modified), not Destructive.
From the tool's definition Tool name 'manage_graph_subscriptions' indicates creation or modification of Microsoft Graph API subscriptions.
Attacks that exploit this kind of access
manage_graph_subscriptions. It is categorised as a Write tool in the Microsoft 365 Core MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft 365 Core MCP Server MCP server in PolicyLayer and add a rule for manage_graph_subscriptions: 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 Microsoft 365 Core MCP Server. Nothing to install.
manage_graph_subscriptions 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 manage_graph_subscriptions 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 manage_graph_subscriptions. 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.
manage_graph_subscriptions is provided by the Microsoft 365 Core MCP Server MCP server (roycedamien/m365-core-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 →