diff --git a/app/chain/download.py b/app/chain/download.py
index 288b3f290..103e26843 100644
--- a/app/chain/download.py
+++ b/app/chain/download.py
@@ -951,6 +951,7 @@ class DownloadChain(ChainBase):
                 seasons=_meta.season,
                 episodes=download_episodes or _meta.episode,
                 image=_media.get_backdrop_image(),
+                poster=_media.get_poster_image(),
                 downloader=_downloader,
                 download_hash=_hash,
                 torrent_name=_torrent.title,
@@ -1777,7 +1778,9 @@ class DownloadChain(ChainBase):
                     "title": history.title,
                     "season": history.seasons,
                     "episode": history.episodes,
-                    "image": history.image,
+                    "image": history.poster,
+                    "poster": history.poster,
+                    "backdrop": history.image,
                 }
                 torrent.site_name = history.torrent_site
                 # 下载用户
diff --git a/app/db/models/downloadhistory.py b/app/db/models/downloadhistory.py
index c39b6b847..5e12922dc 100644
--- a/app/db/models/downloadhistory.py
+++ b/app/db/models/downloadhistory.py
@@ -39,8 +39,10 @@ class DownloadHistory(Base):
     seasons = Column(String)
     # Exx
     episodes = Column(String)
-    # 海报
+    # 背景图
     image = Column(String)
+    # 海报
+    poster = Column(String)
     # 下载器
     downloader = Column(String)
     # 下载任务Hash
diff --git a/app/schemas/history.py b/app/schemas/history.py
index 48fccca18..04f14ea5b 100644
--- a/app/schemas/history.py
+++ b/app/schemas/history.py
@@ -4,6 +4,10 @@ from pydantic import BaseModel, ConfigDict, Field
 
 
 class DownloadHistory(BaseModel):
+    """
+    下载历史记录
+    """
+
     # ID
     id: int
     # 保存路程
@@ -34,8 +38,10 @@ class DownloadHistory(BaseModel):
     seasons: Optional[str] = None
     # 集Exx
     episodes: Optional[str] = None
-    # 海报
+    # 背景图
     image: Optional[str] = None
+    # 海报
+    poster: Optional[str] = None
     # 下载器Hash
     download_hash: Optional[str] = None
     # 种子名称
diff --git a/database/versions/a8c4e2f6b1d9_2_2_15.py b/database/versions/a8c4e2f6b1d9_2_2_15.py
new file mode 100644
index 000000000..34147e102
--- /dev/null
+++ b/database/versions/a8c4e2f6b1d9_2_2_15.py
@@ -0,0 +1,42 @@
+"""2.2.15
+为下载历史增加海报字段
+
+Revision ID: a8c4e2f6b1d9
+Revises: f7b2d5c9a301
+Create Date: 2026-08-03
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+revision = "a8c4e2f6b1d9"
+down_revision = "f7b2d5c9a301"
+branch_labels = None
+depends_on = None
+
+
+def _has_column(table_name: str, column_name: str) -> bool:
+    """检查数据表是否已存在指定字段。"""
+    inspector = sa.inspect(op.get_bind())
+    if table_name not in inspector.get_table_names():
+        return False
+    return any(
+        column["name"] == column_name
+        for column in inspector.get_columns(table_name)
+    )
+
+
+def upgrade() -> None:
+    """为下载历史增加可空海报字段。"""
+    if not _has_column("downloadhistory", "poster"):
+        op.add_column(
+            "downloadhistory",
+            sa.Column("poster", sa.String(), nullable=True),
+        )
+
+
+def downgrade() -> None:
+    """移除下载历史海报字段。"""
+    if _has_column("downloadhistory", "poster"):
+        op.drop_column("downloadhistory", "poster")
diff --git a/docs/mcp-api.md b/docs/mcp-api.md
index 104459706..c1e2fdf9c 100644
--- a/docs/mcp-api.md
+++ b/docs/mcp-api.md
@@ -170,7 +170,7 @@ AniList 榜单、探索、详情、人物和推荐接口优先通过 `anilist-ch
 
 | 方法 | 路径 | 说明 |
 | :--- | :--- | :--- |
-| GET | `/api/v1/download/` | 查询正在下载的任务，参数：`name`；关联下载历史时返回媒体类型及来源站点 `site_name` |
+| GET | `/api/v1/download/` | 查询正在下载的任务，参数：`name`；关联下载历史时返回媒体类型、来源站点 `site_name`，以及 `media.poster` 海报和 `media.backdrop` 背景图；兼容字段 `media.image` 与 `media.poster` 相同 |
 | POST | `/api/v1/download/` | 添加含媒体信息的下载任务，请求体包含媒体信息和种子信息 |
 | POST | `/api/v1/download/add` | 添加不含媒体信息的下载任务，请求体包含 `torrent_in`，可选 `media_source` + `media_id`；继续兼容四种专用 ID，并支持 `downloader`、`save_path` |
 | POST | `/api/v1/download/subtitle` | 下载字幕到识别出的媒体下载目录，请求体包含 `subtitle_in`，可选 `media_source` + `media_id`；继续兼容四种专用 ID，并支持 `save_path` |
@@ -180,6 +180,13 @@ AniList 榜单、探索、详情、人物和推荐接口优先通过 `anilist-ch
 | GET | `/api/v1/download/paths` | 查询可用于下载接口 `save_path` 参数的下载路径 |
 | DELETE | `/api/v1/download/{hashString}` | 删除下载任务，参数：`name` |
 
+#### 历史
+
+| 方法 | 路径 | 说明 |
+| :--- | :--- | :--- |
+| GET | `/api/v1/history/download` | 按下载时间倒序查询下载历史，参数：`page`、`count`；`poster` 为海报，兼容字段 `image` 为背景图 |
+| DELETE | `/api/v1/history/download` | 删除下载历史，请求体为下载历史记录 |
+
 #### 系统
 
 | 方法 | 路径 | 说明 |
diff --git a/skills/moviepilot-api/SKILL.md b/skills/moviepilot-api/SKILL.md
index 286e78b24..a7dd72f14 100644
--- a/skills/moviepilot-api/SKILL.md
+++ b/skills/moviepilot-api/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: moviepilot-api
-version: 6
+version: 7
 description: >-
   Use this skill when you need to call MoviePilot REST API endpoints directly
   with the bundled Python client. Covers MoviePilot HTTP endpoints across media
@@ -251,7 +251,7 @@ Streaming search sends `{"type":"heartbeat"}` every 15 seconds without business
 
 | Method | Path | Description |
 |--------|------|-------------|
-| GET | `/api/v1/history/download` | Download history, newest first. Params: `page`, `count` |
+| GET | `/api/v1/history/download` | Download history, newest first. Params: `page`, `count`. `poster` is the poster image; legacy `image` is the backdrop image. |
 | DELETE | `/api/v1/history/download` | Delete download history. Body: DownloadHistory JSON |
 | GET | `/api/v1/history/transfer` | Transfer history. Params: `title`, `page`, `count`, `status` |
 | DELETE | `/api/v1/history/transfer` | Delete transfer history. Params: `deletesrc`, `deletedest`. Body: TransferHistory |
diff --git a/tests/test_builtin_skill_boundaries.py b/tests/test_builtin_skill_boundaries.py
index 3a68fc134..8adab2cd2 100644
--- a/tests/test_builtin_skill_boundaries.py
+++ b/tests/test_builtin_skill_boundaries.py
@@ -23,7 +23,7 @@ def test_modified_builtin_skills_have_incremented_versions() -> None:
     """本次修改过的内置技能必须递增版本，确保用户端同步更新。"""
     expected_versions = {
         "database-operation": "3",
-        "moviepilot-api": "6",
+        "moviepilot-api": "7",
         "moviepilot-cli": "6",
         "moviepilot-update": "3",
         "transfer-failed-retry": "2",
diff --git a/tests/test_download_chain.py b/tests/test_download_chain.py
index b13f2f618..817c5863d 100644
--- a/tests/test_download_chain.py
+++ b/tests/test_download_chain.py
@@ -249,9 +249,11 @@ def test_download_single_persists_custom_words_snapshot(monkeypatch):
         """捕获写入下载历史的字段，验证识别词快照确实落库。"""
 
         def add(self, **kwargs):
+            """捕获下载历史字段。"""
             captured.update(kwargs)
 
         def add_files(self, _files):
+            """忽略与当前断言无关的下载文件记录。"""
             pass
 
     _FakeThreadHelper.submitted = []
@@ -278,6 +280,8 @@ def test_download_single_persists_custom_words_snapshot(monkeypatch):
             year="2024",
             tmdb_id=1,
             genre_ids=[18],
+            poster_path="https://images.example.com/original/poster.jpg",
+            backdrop_path="https://images.example.com/original/backdrop.jpg",
         ),
         torrent_info=TorrentInfo(
             title="Demo Show 2024",
@@ -298,6 +302,8 @@ def test_download_single_persists_custom_words_snapshot(monkeypatch):
 
     assert result == "hash123"
     assert captured["custom_words"] == custom_words
+    assert captured["poster"] == "https://images.example.com/w500/poster.jpg"
+    assert captured["image"] == "https://images.example.com/w500/backdrop.jpg"
 
 
 def test_save_subtitle_response_creates_missing_temp_directory(monkeypatch, tmp_path):
@@ -1045,7 +1051,8 @@ def test_downloading_includes_media_type_and_source_site(monkeypatch):
     torrent = DownloaderTorrent(hash="download-hash", title="Demo.Release")
     history = SimpleNamespace(
         episodes="E02",
-        image="https://images.example.com/demo.jpg",
+        image="https://images.example.com/backdrop.jpg",
+        poster="https://images.example.com/poster.jpg",
         seasons="S01",
         title="示例剧集",
         tmdbid=1001,
@@ -1066,6 +1073,9 @@ def test_downloading_includes_media_type_and_source_site(monkeypatch):
 
     assert result == [torrent]
     assert torrent.media["type"] == "电视剧"
+    assert torrent.media["image"] == "https://images.example.com/poster.jpg"
+    assert torrent.media["poster"] == "https://images.example.com/poster.jpg"
+    assert torrent.media["backdrop"] == "https://images.example.com/backdrop.jpg"
     assert torrent.site_name == "示例站点"
     assert torrent.userid == "user-1"
     assert torrent.username == "tester"
diff --git a/tests/test_downloadhistory_poster_migration.py b/tests/test_downloadhistory_poster_migration.py
new file mode 100644
index 000000000..6a217241a
--- /dev/null
+++ b/tests/test_downloadhistory_poster_migration.py
@@ -0,0 +1,50 @@
+import importlib
+
+import sqlalchemy as sa
+from alembic.migration import MigrationContext
+from alembic.operations import Operations
+
+
+def test_downloadhistory_poster_migration_adds_and_removes_column(monkeypatch) -> None:
+    """迁移应为下载历史增加可空海报字段，并支持回滚。"""
+    migration = importlib.import_module(
+        "database.versions.a8c4e2f6b1d9_2_2_15"
+    )
+    engine = sa.create_engine("sqlite://")
+    metadata = sa.MetaData()
+    download_history = sa.Table(
+        "downloadhistory",
+        metadata,
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("image", sa.String()),
+    )
+
+    with engine.begin() as connection:
+        metadata.create_all(connection)
+        connection.execute(download_history.insert(), {
+            "id": 1,
+            "image": "https://images.example.com/backdrop.jpg",
+        })
+        context = MigrationContext.configure(connection)
+        monkeypatch.setattr(migration, "op", Operations(context))
+
+        migration.upgrade()
+        migration.upgrade()
+
+        migrated = sa.Table(
+            "downloadhistory",
+            sa.MetaData(),
+            autoload_with=connection,
+        )
+        row = connection.execute(sa.select(migrated)).mappings().one()
+        assert "poster" in migrated.c
+        assert row["image"] == "https://images.example.com/backdrop.jpg"
+        assert row["poster"] is None
+
+        migration.downgrade()
+        rolled_back = sa.Table(
+            "downloadhistory",
+            sa.MetaData(),
+            autoload_with=connection,
+        )
+        assert "poster" not in rolled_back.c