Request additional Microsoft Graph permission scopes by performing a fresh interactive sign-in. This tool only works in interactive authentication mode and should be used if any Graph API call returns permissions related errors.
AI agents use add-graph-permission to create or update resources in Lokka (Microsoft 365 MCP server) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lokka (Microsoft 365 MCP server) environment.
This tool modifies the authentication/authorization state by adding new permission scopes to the application. Granting additional permissions is a reversible write operation (permissions can typically be revoked), but it carries high severity because expanding permissions could allow subsequent tools to perform destructive or financial actions that were previously unauthorized — effectively escalating the blast…
From the tool's definition 'Request additional Microsoft Graph permission scopes by performing a fresh interactive sign-in'
Documented attack patterns abuse exactly the kind of access add-graph-permission gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lokka (Microsoft 365 MCP server), and nothing reaches the server without passing your rules. This is the rule we recommend for add-graph-permission:
{
"version": "1",
"default": "deny",
"tools": {
"add-graph-permission": {
"limits": [
{
"counter": "add-graph-permission_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add-graph-permission 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.
Request additional Microsoft Graph permission scopes by performing a fresh interactive sign-in. This tool only works in interactive authentication mode and should be used if any Graph API call returns permissions related errors. It is categorised as a Write tool in the Lokka (Microsoft 365 MCP server) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lokka (Microsoft 365 MCP server) MCP server in PolicyLayer and add a rule for add-graph-permission: 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 Lokka (Microsoft 365 MCP server). Nothing to install.
add-graph-permission 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-graph-permission 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-graph-permission. 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-graph-permission is provided by the Lokka (Microsoft 365 MCP server) MCP server (merill/lokka). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lokka (Microsoft 365 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.
4 Lokka (Microsoft 365 MCP server) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.