AI agents use send_to_inbox to create or update resources in Dynalist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dynalist environment.
'send_to_inbox' most likely creates or adds content to an inbox (a write operation), reversible by deletion or moving items. Without a concrete description, confidence is moderate. The tool fits the Write category rather than Read (no side effects), Execute (not triggering arbitrary code), Destructive (not irreversible), Financial (no money movement), or Other.
From the tool's definition Tool name is 'send_to_inbox' and sibling tools include 'create_document', 'insert_items', 'edit_items', and 'delete_items', indicating this server manages document creation and modification.
Attacks that exploit this kind of access
${INSTRUCTIONS_FIRST_GUIDANCE}. It is categorised as a Write tool in the Dynalist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dynalist MCP server in PolicyLayer and add a rule for send_to_inbox: 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 Dynalist. Nothing to install.
send_to_inbox 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 send_to_inbox 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 send_to_inbox. 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.
send_to_inbox is provided by the Dynalist MCP server (wawworld/dynalist-mcp). 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 →