Generate an email reply draft (never sends).
AI agents use compose_email_reply to create or update resources in AIOS Co-Founder MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AIOS Co-Founder MCP environment.
The tool creates/writes a draft email, which is a reversible write operation. Since it explicitly never sends the email, there is no risk of unintended communication. The blast radius is low as drafts can be reviewed and discarded.
From the tool's definition "Generate an email reply draft (never sends)" — creates a draft but explicitly does not send
Attacks that exploit this kind of access
Generate an email reply draft (never sends). It is categorised as a Write tool in the AIOS Co-Founder MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AIOS Co-Founder MCP server in PolicyLayer and add a rule for compose_email_reply: 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 AIOS Co-Founder MCP. Nothing to install.
compose_email_reply 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 compose_email_reply 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 compose_email_reply. 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.
compose_email_reply is provided by the AIOS Co-Founder MCP server (varun-b-nagaraj/python-mcp-server). 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 →