AI agents call teams_workspace_extract to retrieve information from Outpost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the sibling tools context (cal_list, contact_list, mail_attachments are all Read operations) and the naming convention using 'extract' (typically implying data retrieval without modification), this appears to be a Read operation that retrieves Teams workspace data. The empty description reduces confidence, but the pattern of other tools on this server and the 'extract' verb suggest no side effects.
From the tool's definition Tool name 'teams_workspace_extract' suggests data retrieval/extraction from Teams workspaces. The description is empty, which limits definitive classification.
Attacks that exploit this kind of access
teams_workspace_extract. It is categorised as a Read tool in the Outpost MCP Server, which means it retrieves data without modifying state.
Register the Outpost MCP server in PolicyLayer and add a rule for teams_workspace_extract: 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 Outpost. Nothing to install.
teams_workspace_extract 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 teams_workspace_extract 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 teams_workspace_extract. 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.
teams_workspace_extract is provided by the Outpost MCP server (signalclaude/outpost). 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 →