Manage email templates stored as drafts in a Templates folder. Templates are draft emails that can be edited and sent. WORKFLOW: 1) User calls get with return_html=false to view simple text body, 2) User provides update instructions to LLM, 3) LLM calls get with return_html=true to retrieve full ...
AI agents use manage_templates to create or update resources in Microsoft Graph MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft Graph MCP Server environment.
This tool modifies email template data (drafts stored in a Templates folder) but does not send them, delete them irreversibly, or access financial systems. The ability to edit templates constitutes a Write action with medium severity due to potential for creating misleading or harmful email content that could be sent later.
From the tool's definition Tool description states it can 'edit' email templates and the workflow shows LLM 'applies' modifications to template HTML content. Verbs like 'manage', 'edit', and 'update' indicate reversible modifications to stored drafts.
Documented attack patterns abuse exactly the kind of access manage_templates gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsoft Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for manage_templates:
{
"version": "1",
"default": "deny",
"tools": {
"manage_templates": {
"limits": [
{
"counter": "manage_templates_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}manage_templates stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage email templates stored as drafts in a Templates folder. Templates are draft emails that can be edited and sent. WORKFLOW: 1) User calls get with return_html=false to view simple text body, 2) User provides update instructions to LLM, 3) LLM calls get with return_html=true to retrieve full HTML, 4) LLM applies user. It is categorised as a Write tool in the Microsoft Graph MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft Graph MCP Server MCP server in PolicyLayer and add a rule for manage_templates: 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 Graph MCP Server. Nothing to install.
manage_templates 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_templates 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_templates. 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_templates is provided by the Microsoft Graph MCP Server MCP server (marlonluo2018/microsoft_graph_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsoft Graph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Microsoft Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.