diff --git a/mcp_server/TOOLS.md b/mcp_server/TOOLS.md
index 18f9ae4..be74044 100644
--- a/mcp_server/TOOLS.md
+++ b/mcp_server/TOOLS.md
@@ -27,6 +27,7 @@ Do not use them as a substitute for formal work definition inside the domain rep
 | `get_domain_summary(domain_slug)` | `domain_slug`: e.g. `"railiance"` | **Domain session start.** Scoped snapshot: active workstreams, blocking decisions, last 5 events, repo SBOM status — ~10% of get_state_summary() token cost. |
 | `get_state_summary()` | — | **Cross-domain work / custodian sessions.** Full snapshot: totals, all blocking decisions, all blocked tasks, all open workstreams, last 20 events. Large (~10k tokens). |
 | `get_topic(slug)` | `slug`: e.g. `"markitect"` | Deep-dive on one topic + its workstreams + recent events. |
+| `list_tasks(workstream_id, status?)` | `workstream_id`: UUID (required); `status?`: todo/in_progress/blocked/done/cancelled | List all tasks in a workstream. Use this to look up task UUIDs before calling `update_task_status`, or to verify which workplan tasks are already synced to the DB. |
 | `list_blocked_tasks(workstream_id?)` | optional filter | Surface all impediments, optionally scoped to one workstream. |
 | `list_pending_decisions(topic_id?)` | optional filter | Decisions holding up work, sorted by deadline. |
 | `get_recent_progress(limit, since?)` | `limit` default 20; `since` ISO datetime | Reconstruct recent session history. |
diff --git a/mcp_server/server.py b/mcp_server/server.py
index 2fec2e0..37fd33a 100644
--- a/mcp_server/server.py
+++ b/mcp_server/server.py
@@ -273,6 +273,21 @@ def get_topic(slug: str) -> str:
     return json.dumps({"topic": topic_detail, "recent_progress": recent}, indent=2)
 
 
+@mcp.tool()
+def list_tasks(workstream_id: str, status: str | None = None) -> str:
+    """List all tasks in a workstream, optionally filtered by status.
+
+    Args:
+        workstream_id: UUID of the workstream (required).
+        status: Optional filter — todo | in_progress | blocked | done | cancelled.
+
+    Returns [{id, title, status, priority, assignee, due_date, needs_human}] for every
+    matching task. Use this to look up task UUIDs before calling update_task_status,
+    or to check which tasks from a workplan file are already synced to the DB.
+    """
+    return json.dumps(_get("/tasks", {"workstream_id": workstream_id, "status": status}), indent=2)
+
+
 @mcp.tool()
 def list_blocked_tasks(workstream_id: str | None = None) -> str:
     """List all tasks with status=blocked, optionally filtered by workstream_id."""