diff --git a/docs/2026-03-23-fable-mcp-design.md b/docs/2026-03-23-fable-mcp-design.md
index 9f05148..aa1a548 100644
--- a/docs/2026-03-23-fable-mcp-design.md
+++ b/docs/2026-03-23-fable-mcp-design.md
@@ -28,6 +28,8 @@ All existing Fable routes use session-based authentication (`session["user_id"]`
 ### Database
 
 New table `api_keys` via migration `0027_add_api_keys.py`:
+- `down_revision = "0026"` (the briefing tables migration)
+- `revision = "0027"`
 
 | Column | Type | Notes |
 |--------|------|-------|
@@ -54,9 +56,11 @@ Full keys are generated as `fmcp_<32 random url-safe chars>`, returned once at c
 
 Session auth is untouched — no regression risk for the web UI.
 
+**Admin routes and API keys:** Routes decorated with `admin_required` check `user.role == "admin"` after auth resolves. API keys authenticate as the key owner — so a write-scoped key for a non-admin user will fail admin-protected routes with 403 (role check, not scope check). This is intentional: API keys cannot elevate privilege beyond the user's role.
+
 ### Routes (`/api/api-keys`)
 
-New blueprint `api_keys_bp`:
+New blueprint `api_keys_bp`, registered in `app.py`:
 
 - `GET /api/api-keys` — list caller's keys (prefix, name, scope, last_used_at, created_at — never the hash or full key)
 - `POST /api/api-keys` — create key; body: `{name, scope}`. Returns full key in response **once only**
@@ -73,9 +77,14 @@ New "API Keys" tab in `SettingsView.vue` (added to `VALID_TABS`):
 
 ### New Search Endpoint
 
-`GET /api/search?q=<query>&type=note|task|all&limit=N`
+`GET /api/search?q=<query>&content_type=note|task|all&limit=N`
 
-Calls the existing `semantic_search_notes()` service (already in `services/embeddings.py`). Returns:
+Calls the existing `semantic_search_notes()` service (already in `services/embeddings.py`). The `content_type` parameter maps to the service's `is_task` argument:
+- `content_type=note` → `is_task=False`
+- `content_type=task` → `is_task=True`
+- `content_type=all` (default) → `is_task=None`
+
+Returns:
 
 ```json
 {
@@ -88,6 +97,37 @@ Calls the existing `semantic_search_notes()` service (already in `services/embed
 
 This endpoint is needed by the MCP's `search.py` tool module. It reuses existing infrastructure with no new ML work.
 
+### Conversation Type: `"mcp"`
+
+A new conversation type `"mcp"` is added alongside `"chat"` and `"briefing"`. This requires changes in two places in the main app:
+
+**`services/chat.py`** — `create_conversation(user_id, title, model)` gains an optional `conversation_type: str = "chat"` parameter, passed through to the `Conversation` constructor.
+
+**`routes/chat.py`** — `POST /api/chat/conversations` accepts an optional `conversation_type` body field (defaults to `"chat"`), passed to `create_conversation`. `GET /api/chat/conversations` continues to default-filter to `conversation_type="chat"` (excluding `"mcp"` and `"briefing"`); pass `?type=mcp` to retrieve MCP conversations.
+
+**Retention:** `cleanup_old_conversations` in `routes/chat.py` currently deletes conversations regardless of type. It must be updated to exclude `conversation_type="mcp"` from the sweep, so MCP audit-trail conversations are not automatically pruned.
+
+MCP conversations:
+- Are created with a caller-supplied name (e.g., `"MCP Session 2026-03-23"`) or auto-named
+- Are excluded from the default chat list
+- Are accessible via `GET /api/chat/conversations?type=mcp` for inspection
+- Appear in the Fable UI if explicitly navigated to, providing an audit trail of MCP-driven interactions
+
+### Chat SSE Wire Format
+
+The MCP's `chat.py` tool must consume the existing SSE stream. The relevant endpoints and event schema:
+
+- **Create conversation:** `POST /api/chat/conversations` → `{id, title, ...}`
+- **Post message + start generation:** `POST /api/chat/conversations/:id/messages` → `{message_id, ...}`; then connect to:
+- **Stream:** `GET /api/chat/conversations/:id/stream` (SSE)
+
+SSE event format (each line is `data: <json>`):
+- `{"type": "token", "content": "..."}` — streaming token
+- `{"type": "tool_call", "name": "...", "result": {...}}` — tool fired
+- `{"type": "done", "content": "...", "tools_used": [...]}` — generation complete; this is the termination event
+
+The MCP tool reads tokens until it receives `type: "done"`, then returns `response` (full content) and `tools_used` (list of tool names).
+
 ---
 
 ## Sub-project 2: Fable MCP Server
@@ -109,12 +149,13 @@ fable-mcp/
     client.py               # FableClient: async httpx wrapper, env var config, FableAPIError
     tools/
       __init__.py
-      notes.py              # list_notes, get_note, create_note, update_note, delete_note, search_notes
+      notes.py              # list_notes, get_note, create_note, update_note, delete_note
       tasks.py              # list_tasks, get_task, create_task, update_task, delete_task,
                             #   patch_task_status, add_task_log
       projects.py           # list_projects, get_project, create_project, update_project,
                             #   delete_project, get_project_summary
-      milestones.py         # list_milestones, get_milestone, create_milestone, update_milestone
+      milestones.py         # list_milestones, get_milestone, create_milestone,
+                            #   update_milestone, delete_milestone
       search.py             # semantic_search — calls GET /api/search
       chat.py               # send_message — creates/continues conversation, returns response
 ```
@@ -172,17 +213,18 @@ Each module imports `_client` from `client.py` and defines tools as `async def`
 - `get_milestone(project_id, milestone_id)`
 - `create_milestone(project_id, title, description, order_index)`
 - `update_milestone(project_id, milestone_id, title, description, status, order_index)`
+- `delete_milestone(project_id, milestone_id)`
 
 **`search.py`** tools:
-- `semantic_search(query, type, limit)` — calls `GET /api/search`, returns ranked results with similarity scores
+- `semantic_search(query, content_type, limit)` — `content_type` is `"note"`, `"task"`, or `"all"` (avoids shadowing Python's `type` builtin). Calls `GET /api/search`, returns ranked results with similarity scores.
 
 **`chat.py`** tools:
 - `send_message(message, conversation_name)`:
-  - Looks up or creates a Fable conversation with the given name and type `"mcp"`
+  - Looks up or creates a Fable conversation with the given name and `conversation_type="mcp"`
   - Posts the message via `POST /api/chat/conversations/:id/messages`
-  - Polls the SSE stream until generation completes
+  - Consumes SSE stream from `GET /api/chat/conversations/:id/stream` until `type: "done"`
   - Returns: `{response: str, tools_used: [str], conversation_id: int}`
-  - MCP conversations use type `"mcp"` and are excluded from the normal chat UI list
+  - MCP conversations are excluded from the normal chat UI list
 
 ### Error Handling
 
@@ -212,16 +254,6 @@ Claude Code spawns the process over stdio automatically. No Docker, no daemon.
 
 ---
 
-## Conversation Type: `"mcp"`
-
-A new conversation type `"mcp"` is added alongside `"chat"` and `"briefing"`. Conversations of this type:
-- Are created with a caller-supplied name (e.g., `"MCP Session 2026-03-23"`) or auto-named
-- Are excluded from `GET /api/chat/conversations` (the main chat list) by default
-- Are accessible via `GET /api/chat/conversations?type=mcp` if inspection is needed
-- Appear in the Fable UI if explicitly navigated to, providing an audit trail of MCP-driven interactions
-
----
-
 ## Build & Repo Plan
 
 1. Implement and test within `fabledassistant/fable-mcp/`