Open and read content for a prior search result. Returns a summary with metadata. Small content is returned inline in the
AI agents call open to retrieve information from M365connector without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool opens and reads content from a prior search result, returning summaries and metadata. This is a read-only operation with no side effects. Severity is medium because it accesses M365 content (potentially sensitive corporate documents, emails, etc.) via a browser extension, but it does not modify or delete anything.
From the tool's definition 'Open and read content for a prior search result. Returns a summary with metadata. Small content is returned inline'
Attacks that exploit this kind of access
Open and read content for a prior search result. Returns a summary with metadata. Small content is returned inline in the. It is categorised as a Read tool in the M365connector MCP Server, which means it retrieves data without modifying state.
Register the M365connector MCP server in PolicyLayer and add a rule for open: 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 M365connector. Nothing to install.
open 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 open 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 open. 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.
open is provided by the M365connector MCP server (m365connector). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →