execute_graph_search · Microsoft 365 Core MCP Server MCP

WHAT IT DOES

What execute_graph_search does on Microsoft 365 Core MCP Server

AI agents invoke execute_graph_search to trigger actions in Microsoft 365 Core MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why execute_graph_search needs a policy

While framed as a search/read operation, the 'execute' terminology and the dynamic nature of user-supplied queries across Microsoft Graph endpoints classify this as Execute rather than Read. An AI agent could misuse this to extract sensitive corporate communications, financial information embedded in emails/files, or calendar details revealing business strategy.

From the tool's definition Tool performs 'Execute advanced search queries' across Microsoft 365 content including emails, files, messages, and calendar events.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_graph_search Rate-limited

execute_graph_search stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_graph_search": {
      "limits": [
        {
          "counter": "execute_graph_search_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Microsoft 365 Core MCP Server, so you can run agents against it safely.

FAQ

Questions about execute_graph_search

What does the execute_graph_search tool do? +

Execute advanced search queries across Microsoft 365 content including emails, files, messages, and calendar events. It is categorised as a Execute tool in the Microsoft 365 Core MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_graph_search? +

Register the Microsoft 365 Core MCP Server MCP server in PolicyLayer and add a rule for execute_graph_search: 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.

What risk level is execute_graph_search? +

execute_graph_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_graph_search? +

Yes. Add a rate_limit block to the execute_graph_search 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.

How do I block execute_graph_search completely? +

Set action: deny in the PolicyLayer policy for execute_graph_search. 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.

What MCP server provides execute_graph_search? +

execute_graph_search 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.