> Discover all available Postdom documentation from the machine-readable index: https://postdom.com/llms.txt

Configured tool · read-only

# `get_plan`

Read the current plan state and structured feedback from the human reviewer.

read-only · non-destructive · closed-world

Human and agent roles

## Configured boundary

### Configured workspace

This read never approves, changes, or cancels a plan. Human authority remains outside the configured agent tool.

This reference describes the hosted server at https://api.postdom.com/mcp, which runs current source, with a workspace-scoped key created under Connected apps → For developers. The published `@postdom/mcp@0.4.0` package has 14 of these tools: it lacks list_posts, create_slideshow, account_music and the media array.

Callable schema

## Input fields

Field names match the configured tool schema. Runtime-only constraints are labeled separately from schema validation.

| Field | Type | Contract |
| --- | --- | --- |
| plan_id Required | UUID | Valid UUID The plan to read inside the configured workspace. |

**For AI agents:** Send only fields exposed by the current tool schema.

**Known failure:** Do not invent platform settings, account IDs, media fields, or setup steps.

Synthetic values

## Example call

Identifiers and values are examples. They do not represent a connected workspace or accepted media source.

_EXAMPLE CALL · CONFIGURED TOOL SCHEMA_

```
get_plan({
  plan_id: "11111111-1111-4111-8111-111111111111"
})
```

Observed API record

## Return shape

Returns the same plan record shape created by submit_plan, refreshed to its current state.

**`id · version · request_hash` (identity)** — Stable plan identity and current review reference.

**`status` (plan state)** — requires_approval, approved, changes_requested, rejected, expired, or cancelled.

**`approval_feedback.decision` (state | null)** — changes_requested or rejected when feedback exists.

**`approval_feedback.category` (category | null)** — caption, media, targeting, timing, policy, or other.

**`approval_feedback.text` (string | null)** — The human reviewer's structured instruction.

**`max_posts · posts_authorized` (integer)** — Plan capacity and posts already authorized.

**`destinations` (array)** — The bounded destination account records.

**`outcome` (object | null)** — Evidence-backed counts, top post, and available metric aggregates after the plan window closes.

Stop conditions

## Agent handoff

`requires_approval`

### Keep waiting

Poll only within the caller's configured budget.

`changes_requested`

### Return feedback

Give the category, text, and exact state to the human workflow.

`approved`

### Proceed in bounds

Use the returned accounts, window, and available capacity.

`rejected · expired · cancelled`

### Stop work

Return the exact state instead of inventing a replacement plan.

**For AI agents:** Return the exact post, plan, and destination states supplied by Postdom.

**Known failure:** Never rename a wire state to action_required or recast a failed, missed, rejected, or revision state as success.

 VERIFIED · 26 AUGUST 2026  **Configured MCP schema · Runtime response model**

Examples are synthetic. Human workspace-key creation and revocation remain in Postdom under Connected apps → For developers.