Submit the composed birding briefing email.
AI agents use submit_email to create or update resources in Birding Planner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Birding Planner environment.
This tool creates and sends an email message, which is a write operation that modifies data (creates a new email record/message in the email system). It is not destructive because emails can typically be unsent or deleted; it does not execute arbitrary code or trigger external operations beyond email submission; and it has no financial impact.
From the tool's definition Tool description states 'Submit the composed birding briefing email.' The word 'submit' indicates sending/storing an email, which creates a new record in an email system and modifies the state of the user's outbox or mail server.
Attacks that exploit this kind of access
Submit the composed birding briefing email. It is categorised as a Write tool in the Birding Planner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Birding Planner MCP server in PolicyLayer and add a rule for submit_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 Birding Planner. Nothing to install.
submit_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 submit_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 submit_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.
submit_email is provided by the Birding Planner MCP server (minikdj/ebird-birding-planner). 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 →