reply_email
A write tool on the Cowork Bench MCP server.
This record as markdown: /tools/cowork-bench/reply-email.md
What reply_email does on Cowork Bench
AI agents use reply_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 reply_email is rated Medium
The name 'reply_email' strongly implies sending an email reply, which is a Write operation (creates a new outbound message). However, the description is empty, so exact behavior is unknown. Severity is medium because sending emails on behalf of a user could have reputational or communication consequences. Confidence is lowered due to the absence of a description.
From the tool's definition Tool name 'reply_email' suggests composing and sending a reply to an existing email message.
Attacks that exploit this kind of access
The rule that runs reply_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 reply_email, this is the rule to start with:
reply_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 reply_email call is checked against it from then on.
Questions about reply_email
reply_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 reply_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.
reply_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 reply_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 reply_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.
reply_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