plan_direct_message_change
Prepare a process-bound keyed plan for one exact private-message send, reply, same-format edit, or irreversible deletion involving one separately configured ordinary Discord user. Send and reply accept plain text, bounded static Components V2, or one independently gated owned local file with opti...
This record as markdown: /tools/app-lasers-guildcontrol-discord/plan-direct-message-change.md
What plan_direct_message_change does on GuildControl MCP
AI agents call plan_direct_message_change to permanently remove resources in GuildControl MCP, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why plan_direct_message_change is rated Critical
Tool permits irreversible deletion of private messages, making it Destructive at high severity.
From the tool's definition irreversible deletion involving one separately configured ordinary Discord user
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs plan_direct_message_change safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GuildControl MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For plan_direct_message_change, this is the rule to start with:
plan_direct_message_change is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect GuildControl MCP, apply this rule, and every plan_direct_message_change call is checked against it from then on.
Questions about plan_direct_message_change
Prepare a process-bound keyed plan for one exact private-message send, reply, same-format edit, or irreversible deletion involving one separately configured ordinary Discord user. Send and reply accept plain text, bounded static Components V2, or one independently gated owned local file with optional text; edit remains text or Components V2 only. Callback-free link rows require every exact canonical HTTPS origin in scopes.componentLinkOrigins before recipient or Discord access, expose every normalized destination in the plan, and are never fetched by the connector. Re-verifies pinned identity, exact participants and message ownership when applicable, complete desired body, fresh file bytes and provenance when present, forced empty mentions, fixed anti-spam limits, privacy omissions, transient review reason, and a unique one-shot operation key without writing or persisting private content. Send planning never opens a DM channel. It is categorised as a Destructive tool in the GuildControl MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GuildControl MCP server in PolicyLayer and add a rule for plan_direct_message_change: 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 GuildControl MCP. Nothing to install.
plan_direct_message_change is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the plan_direct_message_change 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 plan_direct_message_change. 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.
plan_direct_message_change is provided by the GuildControl MCP server (guildctl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GuildControl, and thousands of servers like it.
Across the catalogue