@modudraft/mcp 0.13.1 → 0.14.0

package/README.md

@@ -99,17 +99,22 @@ Copy the key - you'll only see it once.
 | `get_node_schema` | Get expected metadata fields for an archetype |
 
 ### Sequence diagram
+A diagram can hold many named sequences. Each has its own lanes (architecture nodes, in order), messages and fragments. Message and fragment tools take `sequence_id`, which may be left out only when the diagram has exactly one sequence.
+
 | Tool | Description |
 |---|---|
-| `add_sequence_message` | Add a message between two nodes (pass a node id or exact node label; resolved to the node id, which is what the Sequence tab draws) |
-| `bulk_add_sequence_messages` | Add many messages (and optional fragments) in one call; participants resolve to node ids like `add_sequence_message` |
-| `get_sequence` | Read just the sequence: messages (ids, node labels, whether the tab draws them) and fragments; far smaller than `get_diagram` |
+| `list_sequences` | List the sequences: id, name, lanes and message/fragment counts |
+| `add_sequence` | Create a sequence; `path: ["Web", "API", "DB"]` builds lanes Web, API, DB and messages Web→API, API→DB |
+| `update_sequence` | Rename a sequence, change its description, or reorder/replace its lanes |
+| `delete_sequence` | Delete a sequence with its messages and fragments |
+| `add_sequence_participant` | Add a lane (an architecture node) to a sequence |
+| `add_sequence_message` | Add a message between two lanes (pass a node id or exact node label) |
+| `bulk_add_sequence_messages` | Add many messages (and optional fragments) to one sequence in one call |
+| `get_sequence` | Read one sequence: lanes, messages (ids, node labels, whether the tab draws them) and fragments; far smaller than `get_diagram` |
 | `update_sequence_message` | Edit one message in place (sender, receiver, label, type) and/or move it to a new position |
 | `delete_sequence_message` | Delete one message and renumber the rest; fragments that included it are trimmed (or removed if left empty) |
-| `add_sequence_participant` | Register a named participant |
-| `clear_sequence` | Remove all sequence messages |
-| `auto_sequence` | Derive sequence messages from the architecture edges |
-| `add_sequence_fragment` | Wrap messages in a loop / alt / opt / par fragment |
+| `clear_sequence` | Remove all messages and fragments from one sequence (keeps its lanes) |
+| `add_sequence_fragment` | Wrap messages of one sequence in a loop / alt / opt / par fragment |
 | `update_sequence_fragment` | Change a fragment's kind, condition, or message list |
 | `delete_sequence_fragment` | Remove a fragment |
 
@@ -240,7 +245,7 @@ The old `request_body`, `request_format`, `body`, `body_format` and top-level `r
 
 > "Add the DB schema for the order service - orders, order_items, and payments tables."
 
-> "Auto-generate a sequence diagram from the architecture."
+> "Add a Login sequence that goes Web App → API Server → Postgres."
 
 > "What metadata is missing from the diagram nodes? Fill in the hosts and ports based on our .env file."
 
@@ -307,6 +312,7 @@ It draws the **full** tab or a **part** of it. `diagram_type` is `architecture`
 | `boundary` | architecture | `boundary: "VPC"` | the nodes inside that boundary |
 | `archetype` | architecture | `archetype: "database"` | only nodes of that archetype |
 | `from_message` / `to_message` | sequence | `from_message: 13, to_message: 15` | messages 13 to 15 (0-based, inclusive) |
+| `sequence_id` | sequence | `sequence_id: "a1b2c3"` | which sequence (needed when there are several) |
 | `participants` | sequence | `participants: ["Web App", "API Server"]` | only messages between them |
 | `focus` + `hops` + `direction` | er | `focus: "orders", hops: 1` | that table and the tables related to it (`out` = the tables it references, `in` = the tables that reference it) |
 | `tables` / `name_prefix` / `schema` | er | `tables: ["users", "orders"]`, `name_prefix: "order"`, `schema: "audit"` | exactly those tables / tables whose name starts with it / tables of one schema |