forward_email
A write tool on the Cowork Bench MCP server.
This record as markdown: /tools/cowork-bench/forward-email.md
What forward_email does on Cowork Bench
AI agents use forward_email to create or update resources in Cowork Bench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cowork Bench environment.
Why forward_email is rated Medium
The name 'forward_email' strongly implies the tool sends or forwards an email message to one or more recipients, which is a Write/Execute action with external side effects. Forwarding email is reversible in the sense the message can be sent again but cannot be unsent, placing it closer to Execute; however, without a description, confidence is low.
From the tool's definition Tool name 'forward_email' — description is empty and uninformative.
Attacks that exploit this kind of access
The rule that runs forward_email safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For forward_email, this is the rule to start with:
forward_email 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every forward_email call is checked against it from then on.
Questions about forward_email
forward_email is a write tool on the Cowork Bench MCP server. It is categorised as a Write tool in the Cowork Bench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for forward_email: 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 Cowork Bench. Nothing to install.
forward_email 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 forward_email 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 forward_email. 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.
forward_email is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue