Search for a user in Outlook and return their information.
AI agents call search_outlook to retrieve information from MCP Outlook Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches and returns user information from Outlook without creating, modifying, deleting, or executing any operations. It has minimal blast radius if misused by an AI agent — worst case would be unauthorized information disclosure of already-stored contact data. This is clearly a Read category tool.
From the tool's definition Tool description states 'Search for a user in Outlook and return their information' — this is a query operation that retrieves data without modification. Sibling tools like 'get_calendar' and 'search_email' are also read-only retrieval operations.
Documented attack patterns abuse exactly the kind of access search_outlook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Outlook Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for search_outlook:
{
"version": "1",
"default": "deny",
"tools": {
"search_outlook": {}
}
}search_outlook is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for a user in Outlook and return their information. It is categorised as a Read tool in the MCP Outlook Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Outlook Tools MCP server in PolicyLayer and add a rule for search_outlook: 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 MCP Outlook Tools. Nothing to install.
search_outlook is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_outlook 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 search_outlook. 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.
search_outlook is provided by the MCP Outlook Tools MCP server (wmoto-ai/mcp-outlook-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Outlook Tools, 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.
6 MCP Outlook Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.