A versatile tool to interact with Microsoft APIs including Microsoft Graph (Entra) and Azure Resource Management. IMPORTANT: For Graph API GET requests using advanced query parameters ($filter, $count, $search, $orderby), you are ADVISED to set
AI agents use Lokka-Microsoft to create or update resources in Lokka (Microsoft 365 MCP server) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lokka (Microsoft 365 MCP server) environment.
While the tool supports read operations (query, GET), the explicit mention of 'update all resources in your Microsoft 365 tenant' makes it capable of modifying data reversibly. This qualifies as Write category. Severity is high because misconfigured permissions or prompt injection could allow modification of sensitive Microsoft 365 tenant data (emails, documents, user profiles, security settings).
From the tool's definition Tool description states 'interact with Microsoft APIs including Microsoft Graph' and server description explicitly mentions 'query and update all resources in your Microsoft 365 tenant' with 'update operations'.
Documented attack patterns abuse exactly the kind of access Lokka-Microsoft gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lokka (Microsoft 365 MCP server), and nothing reaches the server without passing your rules. This is the rule we recommend for Lokka-Microsoft:
{
"version": "1",
"default": "deny",
"tools": {
"Lokka-Microsoft": {
"limits": [
{
"counter": "lokka-microsoft_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}Lokka-Microsoft stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
A versatile tool to interact with Microsoft APIs including Microsoft Graph (Entra) and Azure Resource Management. IMPORTANT: For Graph API GET requests using advanced query parameters ($filter, $count, $search, $orderby), you are ADVISED to set. 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 Lokka-Microsoft: 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.
Lokka-Microsoft 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 Lokka-Microsoft 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 Lokka-Microsoft. 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.
Lokka-Microsoft 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.