refactor(mcp): remove canvas tool and resource write endpoints

.claude/commands/test-live.md

@@ -45,8 +45,7 @@ When the user runs `/project:test-live`, execute comprehensive test plan:
 16. **edit_note** (advanced modes) - Complex find/replace operations
 
 ### **Tier 4: Specialized (Rarely Test)**
-17. **canvas** - Obsidian visualization (specialized use case)
-18. **MCP Prompts** - Enhanced UX tools (ai_assistant_guide, continue_conversation)
+17. **MCP Prompts** - Enhanced UX tools (ai_assistant_guide, continue_conversation)
 
 ## Stateless Architecture Testing
 
@@ -308,13 +307,7 @@ Test essential MCP tools that form the foundation of Basic Memory:
 
 ### Phase 6: Specialized Tools Testing (Tier 4)
 
-**16. canvas Tests (Specialized):**
-- ✅ JSON Canvas generation
-- ✅ Node and edge creation
-- ✅ Obsidian compatibility
-- ⚠️ Complex graph handling
-
-**17. MCP Prompts Tests (Specialized):**
+**16. MCP Prompts Tests (Specialized):**
 - ✅ ai_assistant_guide output
 - ✅ continue_conversation functionality
 - ✅ Formatted search results

AGENTS.md

@@ -423,9 +423,6 @@ See `.claude/commands/release/release.md` (and `beta.md`, `release-check.md`, `c
     - `create_memory_project(project_name, project_path, set_default)` - Create new Basic Memory projects
     - `delete_project(project_name)` - Delete a project from configuration
 
-  **Visualization:**
-    - `canvas(nodes, edges, title, directory)` - Generate Obsidian canvas files for knowledge graph visualization
-
   **ChatGPT-Compatible Tools:**
     - `search(query)` - Search across knowledge base (OpenAI actions compatible)
     - `fetch(id)` - Fetch full content of a search result document

README.md

@@ -491,8 +491,7 @@ agents can pick the right one without trial-and-error:
   `delete_note`, `read_content`, `view_note`
 - **Search & discovery:** `search`, `search_notes`, `recent_activity`,
   `list_directory`
-- **Knowledge graph:** `build_context` (navigates `memory://` URLs),
-  `canvas` (Obsidian canvas generation)
+- **Knowledge graph:** `build_context` (navigates `memory://` URLs)
 - **Projects:** `list_memory_projects`, `create_memory_project`,
   `get_current_project`, `sync_status`
 - **Schema:** `schema_infer`, `schema_validate`, `schema_diff`

docs/ai-assistant-guide-extended.md

@@ -2472,73 +2472,25 @@ except:
 
 ### Knowledge Graph Visualization
 
-**Create visual representation using canvas**:
+**Create visual representations with Obsidian canvas files**:
 
-```python
-# Gather entities to visualize
-auth_context = await build_context(
-    url="memory://Authentication System",
-    depth=2,
-    project="main"
-)
-
-# Create nodes
-nodes = [
-    {
-        "id": "auth-system",
-        "type": "file",
-        "file": "specs/authentication-system.md",
-        "x": 0,
-        "y": 0,
-        "width": 400,
-        "height": 300
-    },
-    {
-        "id": "user-db",
-        "type": "file",
-        "file": "services/user-database.md",
-        "x": 500,
-        "y": 0,
-        "width": 400,
-        "height": 300
-    },
-    {
-        "id": "login-api",
-        "type": "file",
-        "file": "api/login-api.md",
-        "x": 250,
-        "y": 400,
-        "width": 400,
-        "height": 300
-    }
-]
-
-# Create edges showing relations
-edges = [
-    {
-        "id": "edge-1",
-        "fromNode": "auth-system",
-        "toNode": "user-db",
-        "label": "requires"
-    },
-    {
-        "id": "edge-2",
-        "fromNode": "auth-system",
-        "toNode": "login-api",
-        "label": "implemented_by"
-    }
-]
-
-# Generate canvas
-canvas = await canvas(
-    nodes=nodes,
-    edges=edges,
-    title="Authentication System Overview",
-    folder="diagrams",
-    project="main"
-)
+Gather entities with `build_context`, then write a
+[JSON Canvas](https://jsoncanvas.org/) file (`.canvas`) into the project
+directory. Basic Memory indexes `.canvas` files as JSON, and Obsidian opens
+them for interactive exploration:
 
-# Opens in Obsidian for interactive exploration
+```json
+{
+  "nodes": [
+    {"id": "auth-system", "type": "file", "file": "specs/authentication-system.md", "x": 0, "y": 0, "width": 400, "height": 300},
+    {"id": "user-db", "type": "file", "file": "services/user-database.md", "x": 500, "y": 0, "width": 400, "height": 300},
+    {"id": "login-api", "type": "file", "file": "api/login-api.md", "x": 250, "y": 400, "width": 400, "height": 300}
+  ],
+  "edges": [
+    {"id": "edge-1", "fromNode": "auth-system", "toNode": "user-db", "label": "requires"},
+    {"id": "edge-2", "fromNode": "auth-system", "toNode": "login-api", "label": "implemented_by"}
+  ]
+}
 ```
 
 ### Progressive Knowledge Building
@@ -3090,28 +3042,6 @@ status = await sync_status(project="main")
 workspaces = await list_workspaces()
 ```
 
-### Visualization
-
-**canvas(nodes, edges, title, folder, project)**
-- Create Obsidian canvas
-- Parameters:
-  - `nodes` (required): List of node objects
-  - `edges` (required): List of edge objects
-  - `title` (required): Canvas title
-  - `folder` (required): Destination folder
-  - `project` (required unless default_project_mode): Target project
-- Returns: Created canvas file
-- Example:
-```python
-await canvas(
-    nodes=[{"id": "1", "type": "file", "file": "note.md", "x": 0, "y": 0}],
-    edges=[],
-    title="Graph View",
-    folder="diagrams",
-    project="main"
-)
-```
-
 ---
 
 ## Best Practices

skills/memory-literary-analysis/SKILL.md

@@ -23,7 +23,7 @@ Phase 1: Seed          → stub notes for known major entities
 Phase 2: Process       → chapter-by-chapter notes in batches
 Phase 3: Cross-ref     → enrich arcs, add parallels, write analysis
 Phase 4: Validate      → schema checks, drift detection, consistency
-Phase 5: Visualize     → canvas files for character webs, timelines
+Phase 5: Visualize     → Obsidian canvas files for character webs, timelines
 ```
 
 ## Phase 0: Setup
@@ -451,19 +451,22 @@ Spot-check bidirectional relations: if Chapter X `features [[Character]]`, does
 
 ## Phase 5: Visualization
 
-Generate canvas files for visual exploration:
-
-```python
-# Character relationship web
-canvas(query="type:Character AND role:protagonist OR role:antagonist OR role:supporting")
-
-# Theme connections
-canvas(query="type:Theme")
-
-# Chapter timeline with key events
-canvas(query="type:Chapter", layout="timeline")
+Write [JSON Canvas](https://jsoncanvas.org/) files (`.canvas`) into the project directory for visual exploration in Obsidian. Query the graph first (`search_notes`, `build_context`), then lay out the results as canvas nodes and edges:
+
+```json
+{
+  "nodes": [
+    {"id": "ahab", "type": "file", "file": "characters/captain-ahab.md", "x": 0, "y": 0, "width": 400, "height": 300},
+    {"id": "ishmael", "type": "file", "file": "characters/ishmael.md", "x": 500, "y": 0, "width": 400, "height": 300}
+  ],
+  "edges": [
+    {"id": "e1", "fromNode": "ishmael", "toNode": "ahab", "label": "narrates"}
+  ]
+}
 ```
 
+Useful canvases: character relationship web (protagonist/antagonist/supporting), theme connections, chapter timeline with key events.
+
 ## Adapting to Other Genres
 
 This pipeline works for any literary text. Adjust schemas for genre: