plan_guild_blueprint

Prepare the next process-bound frontier of one caller-retained declarative Discord guild blueprint. The result overlays every normalized manifest entry with freshly-assessed or deferred live status, while only the current complete-evidence frontier can be executable; it never simulates future Discord IDs or post-write state. Additive structure, exact-ID role configuration, bottom-up exact or receipt-bound role-order adjacency, exact-ID channel metadata, bottom-up exact or receipt-bound channel-order adjacency, exact-channel one-target permission-overwrite convergence, profile, settings, monotonic Community enablement and routing, Welcome Screen, onboarding, staged AutoMod, and ordered static Components V2 publications delegate to their existing complete-evidence domains in a fixed order. Role-configuration, channel-metadata, and overwrite collections are canonicalized by snowflake and target identity; roleOrder and channelOrders preserve their semantic top-to-bottom chains. Channel-order references are globally unique before and after resolution. Each adjacency preserves exact permission overwrites and requires complete affected groups, capacity, movement authority, one non-retried write, and newer coherent Gateway plus HTTP readback. A live cross-parent adjacency returns a content-free blocker unless its chain contains literal acknowledgeReparenting=true; permission synchronization is never implied. No live target is matched by name. Every hierarchy, ordering, or overwrite frontier retains its standalone capability, exact scope, permission, receipt, coordination, non-retry, and readback gates. A completed matching nested receipt satisfies only fresh exact current state; drift blocks key reuse. A requested enabled Welcome Screen or onboarding phase is blocked early when Community is disabled and no acknowledged Community phase can establish it. Unbound AutoMod creation recovers identity only from a matching content-free request-bound receipt, never a name scan; exact existing rules use exact IDs, and policy changes advance through separate disable, configure, and enable reviews. Publication recovery uses content-free keyed receipts and one exact receipt-bound message read, never a history scan. Requested scaffold channel and role keys become exact domain references only where permitted. Returns one transient frontier or content-free channel-ordering, Community, AutoMod, or publication blocker while persisting neither the manifest nor its content. It is categorised as a Write tool in the GuildControl MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

Register the GuildControl MCP server in PolicyLayer and add a rule for plan_guild_blueprint: 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_guild_blueprint 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 plan_guild_blueprint 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_guild_blueprint. 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_guild_blueprint 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.