de en es ja ko ru zh

io.github.Airta-Admin/davinc-resolve-local-bridge-mcp

Name: io.github.Airta-Admin/davinc-resolve-local-bridge-mcp
Author: Airta-Admin

by Airta-Admin

Overview Schema Source Related Servers Discussions Admin

Python

Local

Davinc-Resolve-Local-Bridge-MCP

这是什么？

Davinc-Resolve-Local-Bridge-MCP 是一个 Model Context Protocol (MCP) 服务器，让 AI 助手能够完全控制 DaVinci Resolve。它提供 215 个工具，覆盖整个 Resolve 脚本 API——项目、时间线、媒体、Fusion、调色、渲染等。

工作原理

Your AI Assistant (Claude, Cursor, Devin, etc.)
       │
       │  talks MCP (stdio)
       ▼
  mcp_server/server.py        ← runs on your machine
       │
       │  talks HTTP (localhost:8787)
       ▼
  Bridge-Connection-Script.py ← runs INSIDE DaVinci Resolve
       │                        (Workspace > Scripts menu)
       ▼
  DaVinci Resolve API         ← full read + write access

桥接脚本在 DaVinci Resolve 进程内部运行，使其能够完全访问 Resolve 脚本 API——即使在 Free 版（该版本会阻止外部脚本）上也是如此。MCP 服务器作为独立进程运行，并通过 localhost HTTP 将工具调用代理到桥接器。

Related MCP server: davinci-resolve-mcp

快速开始

前置要求

DaVinci Resolve 18.5+（Free 或 Studio）
你的机器上安装 Python 3.10+
兼容 MCP 的 AI 助手（Claude Desktop、Cursor、Devin 等）

第 1 步 — 安装桥接脚本

运行安装程序：

python install.py

或者手动将 bridge/Bridge-Connection-Script.py 复制到 Resolve 的脚本文件夹：

平台	路径
Windows	`%APPDATA%\Roaming\Blackmagic Design\DaVinci Resolve\Support\Fusion\Scripts\Utility\`
macOS	`~/Library/Application Support/Blackmagic Design/DaVinci Resolve/Fusion/Scripts/Utility/`
Linux	`~/.local/share/DaVinciResolve/Fusion/Scripts/Utility/`

第 2 步 — 安装 MCP 服务器依赖

pip install -r requirements.txt

第 3 步 — 配置你的 AI 助手

将 MCP 服务器添加到你的助手配置文件中。服务器路径是本仓库中的 mcp_server/server.py。

Claude Desktop

编辑 claude_desktop_config.json：

{
  "mcpServers": {
    "davinci-resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Cursor

编辑 .cursor/mcp.json：

{
  "mcpServers": {
    "davinci-resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Devin

编辑 mcp_config.json：

{
  "mcpServers": {
    "resolve-local-bridge": {
      "command": "python",
      "args": ["C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py"]
    }
  }
}

Claude Code

claude mcp add davinci-resolve-local-bridge -- python C:/path/to/Davinc-Resolve-Local-Bridge-MCP/mcp_server/server.py

任意 MCP 客户端（通用）

服务器使用 stdio 传输。使用以下命令启动：

python mcp_server/server.py

第 4 步 — 在 DaVinci Resolve 中启动桥接器

打开 DaVinci Resolve
转到 Workspace → Scripts → Bridge-Connection-Script
在 Console（Workspace → Console）中查看：

[Resolve Bridge] Connected to Resolve 21.0.4.5
[Resolve Bridge] HTTP server running on http://127.0.0.1:8787
[Resolve Bridge] 215 actions available

第 5 步 — 开始使用

向你的 AI 助手提问：

"检查 DaVinci Resolve 是否已连接"

助手将调用 resolve_status 工具并返回结果。然后尝试：

"创建一个名为 'My Video' 的 1920x1080 30fps 新项目并添加时间线"

架构

桥接脚本（`bridge/Bridge-Connection-Script.py`）

一个通过 Workspace > Scripts 菜单在 DaVinci Resolve 内部运行的 Python 脚本。它：

从 Fusion 的全局变量中获取实时的 resolve 对象
在 127.0.0.1:8787 上启动 HTTP 服务器
提供 3 个端点：
- GET /health — 检查桥接器是否存活
- GET /actions — 列出所有可用的操作名称
- POST /action — 按名称执行操作并传入参数
通过阻塞式 serve_forever() 调用保持运行
启动前会终止同一端口上的任何先前实例

MCP 服务器（`mcp_server/server.py`）

一个独立的 MCP 服务器，它：

通过 localhost 上的 HTTP 连接到桥接器
从桥接器的 /actions 端点自动发现全部 215 个操作
将每个操作作为带有 resolve_ 前缀的 MCP 工具公开
通过 POST /action 将工具调用代理到桥接器
与桥接器保持同步——无需手动定义工具

全部 215 个工具

MCP 服务器从桥接器自动发现工具。每个工具都带有 resolve_ 前缀（例如，status 变为 resolve_status）。通过 params 对象传递参数。

Resolve 应用程序（15 个工具）

工具	参数	描述
`resolve_status`	—	检查桥接连接状态并获取当前项目/时间线信息
`resolve_get_version`	—	获取 Resolve 版本信息
`resolve_get_current_page`	—	获取当前活动页面（edit、cut、color 等）
`resolve_open_page`	`page`	切换到指定页面：edit、cut、fusion、color、fairlight、deliver、media
`resolve_get_layout_presets`	—	列出可用的布局预设
`resolve_load_layout_preset`	`presetName`	按名称加载布局预设
`resolve_get_keyframe_mode`	—	获取当前关键帧模式
`resolve_set_keyframe_mode`	`keyframeMode`	设置关键帧模式
`resolve_get_fairlight_presets`	—	列出 Fairlight 音频预设
`resolve_get_burnin_presets`	—	列出烧录预设
`resolve_import_render_preset`	`presetPath`	从文件导入渲染预设
`resolve_export_render_preset`	`presetName`, `exportPath`	将渲染预设导出到文件
`resolve_open_fusion_page`	—	切换到 Fusion 页面
`resolve_open_edit_page`	—	切换到 Edit 页面
`resolve_open_deliver_page`	—	切换到 Deliver 页面

项目管理器（18 个工具）

工具	参数	描述
`resolve_create_project`	`name`, `width`, `height`, `fps`	创建新项目
`resolve_load_project`	`name`	加载现有项目
`resolve_save_project`	—	保存当前项目
`resolve_close_project`	—	关闭当前项目
`resolve_delete_project`	`name`	删除项目
`resolve_create_folder`	`folderName`	创建项目文件夹
`resolve_delete_folder`	`folderName`	删除项目文件夹
`resolve_get_project_list`	—	列出当前文件夹中的项目
`resolve_get_folder_list`	—	列出当前文件夹中的子文件夹
`resolve_get_current_folder`	—	获取当前文件夹名称
`resolve_open_folder`	`folderName`	打开文件夹
`resolve_goto_root_folder`	—	导航到根文件夹
`resolve_goto_parent_folder`	—	导航到父文件夹
`resolve_import_project`	`filePath`, `projectName`	导入 .drp 项目
`resolve_export_project`	`projectName`, `filePath`, `withStillsAndLUTs`	将项目导出为 .drp
`resolve_archive_project`	`projectName`, `filePath`, ...	归档项目
`resolve_get_current_database`	—	获取当前数据库名称
`resolve_get_database_list`	—	列出可用数据库

项目设置（7 个工具）

工具	参数	描述
`resolve_get_project_name`	—	获取当前项目名称
`resolve_set_project_name`	`name`	重命名当前项目
`resolve_get_project_setting`	`key`	按键获取项目设置
`resolve_set_project_setting`	`key`, `value`	设置项目设置
`resolve_get_project_settings`	—	获取所有项目设置
`resolve_get_project_preset_list`	—	列出项目预设
`resolve_set_project_preset`	`presetName`	应用项目预设

媒体存储（4 个工具）

工具	参数	描述
`resolve_get_mounted_volumes`	—	列出已挂载的存储卷
`resolve_get_subfolder_list`	`folderPath`	列出路径中的子文件夹
`resolve_get_file_list`	`folderPath`	列出文件夹中的文件
`resolve_reveal_in_storage`	`path`	在操作系统文件浏览器中显示文件

媒体池（13 个工具）

工具	参数	描述
`resolve_import_media`	`paths`（列表）	将媒体文件导入媒体池
`resolve_get_media_pool`	—	列出根文件夹中的所有片段
`resolve_get_root_folder`	—	获取根文件夹信息
`resolve_add_sub_folder`	`folderName`, `parentFolderName`	创建子文件夹
`resolve_set_current_folder`	`folderName`	设置当前文件夹
`resolve_delete_clips`	`clipNames`（列表）	从媒体池中删除片段
`resolve_move_clips`	`clipNames`, `targetFolder`	将片段移动到文件夹
`resolve_relink_clips`	`clipNames`, `folderPath`	重新链接片段
`resolve_unlink_clips`	`clipNames`	取消链接片段
`resolve_export_metadata`	`fileName`, `clipNames`	导出元数据 CSV
`resolve_get_selected_clips`	—	列出选中的片段
`resolve_set_selected_clip`	`clipName`	选择片段
`resolve_add_timeline_mattes`	`paths`（列表）	添加遮罩文件

时间线（21 个工具）

工具	参数	描述
`resolve_create_timeline`	`name`	创建新的空时间线
`resolve_create_timeline_from_clips`	`name`, `clipNames`	从片段创建时间线
`resolve_list_timelines`	—	列出所有时间线
`resolve_get_timeline_name`	—	获取当前时间线名称
`resolve_set_timeline_name`	`name`	重命名当前时间线
`resolve_set_current_timeline`	`timelineIndex`	按索引切换时间线（从1开始）
`resolve_duplicate_timeline`	—	复制当前时间线
`resolve_delete_timelines`	`timelineNames`	删除时间线
`resolve_get_timeline_start_frame`	—	获取起始帧
`resolve_get_timeline_end_frame`	—	获取结束帧
`resolve_get_start_timecode`	—	获取起始时间码
`resolve_set_start_timecode`	`timecode`	设置起始时间码
`resolve_get_current_timecode`	—	获取当前时间码
`resolve_set_current_timecode`	`timecode`	设置当前时间码
`resolve_detect_scene_cuts`	—	检测场景剪切
`resolve_create_subtitles_from_audio`	`settings`	自动生成字幕
`resolve_timeline_export`	`fileName`, `exportType`, `exportSubtype`	导出时间线
`resolve_import_timeline_from_file`	`filePath`	从文件导入时间线
`resolve_append_to_timeline`	`clipNames`	将片段追加到时间线
`resolve_get_timeline_setting`	`key`	获取时间线设置
`resolve_set_timeline_setting`	`key`, `value`	设置时间线设置

时间线轨道（11个工具）

工具	参数	描述
`resolve_get_track_count`	`trackType`	统计轨道数量（视频/音频/字幕）
`resolve_add_track`	`trackType`	添加轨道
`resolve_delete_track`	`trackType`, `trackIndex`	删除轨道
`resolve_set_track_enable`	`trackType`, `trackIndex`, `enabled`	启用/禁用轨道
`resolve_get_track_enable`	`trackType`, `trackIndex`	检查轨道是否启用
`resolve_set_track_lock`	`trackType`, `trackIndex`, `locked`	锁定/解锁轨道
`resolve_get_track_lock`	`trackType`, `trackIndex`	检查轨道是否锁定
`resolve_get_track_name`	`trackType`, `trackIndex`	获取轨道名称
`resolve_set_track_name`	`trackType`, `trackIndex`, `name`	设置轨道名称
`resolve_get_items_in_track`	`trackType`, `index`	列出轨道上的片段
`resolve_get_timeline_selected_clips`	—	列出选中的时间线片段

时间线片段（66个工具）

所有片段操作都接受可选的 trackType、trackIndex、itemIndex 来定位特定片段，如果省略则作用于第一个选中的片段。

Tool	Parameters	Description
`resolve_get_item_name`	`trackType?`, `trackIndex?`, `itemIndex?`	获取片段名称
`resolve_set_item_name`	`name`, `trackType?`, ...	重命名片段
`resolve_get_item_duration`	`trackType?`, ...	获取片段时长
`resolve_get_item_start`	`trackType?`, ...	获取片段起始帧
`resolve_get_item_end`	`trackType?`, ...	获取片段结束帧
`resolve_get_item_property`	`key?`, `trackType?`, ...	获取片段属性
`resolve_set_item_property`	`key`, `value`, `trackType?`, ...	设置片段属性
`resolve_get_item_enabled`	`trackType?`, ...	检查片段是否启用
`resolve_set_item_enabled`	`enabled`, `trackType?`, ...	启用/禁用片段
`resolve_set_item_color`	`colorName`, `trackType?`, ...	设置片段颜色
`resolve_get_item_color`	`trackType?`, ...	获取片段颜色
`resolve_clear_item_color`	`trackType?`, ...	清除片段颜色
`resolve_add_item_flag`	`color`, `trackType?`, ...	添加标记
`resolve_get_item_flags`	`trackType?`, ...	获取标记
`resolve_clear_item_flags`	`color`, `trackType?`, ...	清除标记
`resolve_add_item_marker`	`frameId`, `color`, `name`, `note?`, ...	添加标记点
`resolve_get_item_markers`	`trackType?`, ...	获取标记点
`resolve_insert_generator`	`generatorName`	插入生成器
`resolve_insert_fusion_generator`	`generatorName`	插入 Fusion 生成器
`resolve_insert_fusion_composition`	—	插入 Fusion 合成
`resolve_insert_ofx_generator`	`generatorName`	插入 OFX 生成器
`resolve_insert_title`	`titleName`	插入标题
`resolve_insert_fusion_title`	`titleName`	插入 Fusion 标题
`resolve_grab_still`	—	从当前帧抓取静帧
`resolve_grab_all_stills`	—	从所有片段抓取静帧
`resolve_create_compound_clip`	`name`	创建复合片段
`resolve_create_fusion_clip`	—	创建 Fusion 片段
`resolve_import_into_timeline`	`filePath`, `importOptions?`	导入到时间线
`resolve_stabilize`	`trackType?`, ...	稳定片段
`resolve_smart_reframe`	`trackType?`, ...	智能重构片段
`resolve_create_magic_mask`	`mode`, `trackType?`, ...	创建 Magic Mask
`resolve_regenerate_magic_mask`	`trackType?`, ...	重新生成 Magic Mask
`resolve_get_item_track_info`	`trackType?`, ...	获取片段的轨道信息
`resolve_get_linked_items`	`trackType?`, ...	获取关联项
`resolve_set_item_cdl`	`cdl`, `trackType?`, ...	设置 CDL 值
`resolve_add_take`	`mediaPoolItemName`, `startFrame?`, `endFrame?`	添加一个 take
`resolve_get_takes_count`	`trackType?`, ...	统计 take 数量
`resolve_select_take_by_index`	`idx`, `trackType?`, ...	选择 take
`resolve_finalize_take`	`trackType?`, ...	完成当前 take
`resolve_copy_grades`	`targetItemNames`, `trackType?`, ...	将调色复制到其他片段
`resolve_export_lut`	`exportType`, `path`, `trackType?`, ...	导出 LUT
`resolve_set_color_output_cache`	`cache_value`, `trackType?`, ...	设置颜色输出缓存
`resolve_set_fusion_output_cache`	`cache_value`, `trackType?`, ...	设置 Fusion 输出缓存
`resolve_get_clip_metadata`	`metadataType?`	获取片段元数据
`resolve_set_clip_metadata`	`metadataType`, `metadataValue`	设置片段元数据
`resolve_get_clip_property`	`propertyName?`	获取片段属性
`resolve_set_clip_property`	`propertyName`, `propertyValue`	设置片段属性
`resolve_link_proxy_media`	`proxyMediaFilePath`	链接代理媒体
`resolve_unlink_proxy_media`	—	取消链接代理媒体
`resolve_replace_clip`	`filePath`	用文件替换片段
`resolve_add_clip_marker`	`frameId`, `color`, `name`, `note?`	添加片段标记点
`resolve_get_clip_markers`	—	获取片段标记点
`resolve_set_clip_color`	`colorName`	设置片段颜色（媒体池）
`resolve_add_clip_flag`	`color`	添加片段标记
`resolve_transcribe_clip_audio`	`useSpeakerDetection?`	转录音频
`resolve_set_clip_mark_inout`	`markIn`, `markOut`, `type`	设置入点/出点
`resolve_clear_clip_mark_inout`	`type`	清除入点/出点
`resolve_add_timeline_marker`	`frameId`, `color`, `name`, `note?`	添加时间线标记点
`resolve_get_timeline_markers`	—	获取时间线标记点
`resolve_delete_timeline_markers_by_color`	`color`	按颜色删除标记点
`resolve_delete_timeline_marker_at_frame`	`frameNum`	删除指定帧的标记点
`resolve_export_current_frame`	`filePath`	将当前帧导出为静帧
`resolve_apply_fairlight_preset`	`name`	应用 Fairlight 预设
`resolve_get_quick_export_presets`	—	列出快速导出预设

Fusion 合成（14 个工具）

Tool	Parameters	Description
`resolve_create_fusion_comp`	`name`	创建 Fusion 合成
`resolve_add_fusion_comp`	`trackType?`, ...	向片段添加 Fusion 合成
`resolve_import_fusion_comp`	`path`, `trackType?`, ...	导入 .comp 文件
`resolve_export_fusion_comp`	`path`, `compIndex?`, `trackType?`, ...	导出 Fusion 合成
`resolve_load_fusion_comp_by_name`	`compName`, `trackType?`, ...	按名称加载合成
`resolve_delete_fusion_comp_by_name`	`compName`, `trackType?`, ...	按名称删除合成
`resolve_rename_fusion_comp`	`oldName`, `newName`, `trackType?`, ...	重命名合成
`resolve_get_item_fusion_comp_count`	`trackType?`, ...	统计片段上的 Fusion 合成数量
`resolve_get_item_fusion_comp_names`	`trackType?`, ...	列出 Fusion 合成名称
`resolve_get_current_comp`	—	获取当前 Fusion 合成
`resolve_fusion_get_comp_list`	—	列出所有打开的合成
`resolve_fusion_new_comp`	—	创建新的 Fusion 合成
`resolve_fusion_save_comp`	`filePath`	保存当前合成
`resolve_fusion_load_comp`	`filePath`	加载合成文件
`resolve_fusion_close_comp`	—	关闭当前合成
`resolve_fusion_render_comp`	—	渲染当前合成

Fusion 工具（11 个工具）

工具	参数	描述
`resolve_fusion_get_tool_list`	—	列出当前合成中的所有工具/节点
`resolve_fusion_find_tool`	`name`	按名称查找工具
`resolve_fusion_delete_tool`	`name`	删除工具
`resolve_fusion_get_attrs`	`name`	获取工具属性
`resolve_fusion_set_attrs`	`name`, `attrs`	设置工具属性
`resolve_fusion_add_node`	`nodeType`, `name`	添加节点（Background、Paint、Merge 等）
`resolve_fusion_connect`	`fromNode`, `toNode`, `input`	连接两个节点
`resolve_fusion_set_input`	`node`, `input`, `value`, `frame?`	设置节点输入（可设置关键帧）
`resolve_fusion_get_input`	`node`, `input`	获取节点输入值
`resolve_fusion_set_current_frame`	`frame`	设置当前帧
`resolve_fusion_get_current_frame`	—	获取当前帧

画廊（4 个工具）

工具	参数	描述
`resolve_get_gallery_still_albums`	—	列出画廊静帧相册
`resolve_get_gallery_powergrade_albums`	—	列出 PowerGrade 相册
`resolve_create_gallery_still_album`	—	创建静帧相册
`resolve_create_powergrade_album`	—	创建 PowerGrade 相册

调色 / 节点（7 个工具）

工具	参数	描述
`resolve_get_node_count`	—	获取当前片段的节点数量
`resolve_get_node_label`	`nodeIndex`	获取节点标签
`resolve_get_node_lut`	`nodeIndex`	获取节点的 LUT
`resolve_set_node_lut`	`nodeIndex`, `lutPath`	在节点上设置 LUT
`resolve_set_node_enabled`	`nodeIndex`, `isEnabled`	启用/禁用节点
`resolve_reset_all_grades`	—	重置所有调色
`resolve_refresh_lut_list`	—	刷新 LUT 列表

渲染（22 个工具）

工具	参数	描述
`resolve_get_render_formats`	—	列出渲染格式
`resolve_get_render_codecs`	`renderFormat`	列出某格式的编解码器
`resolve_get_current_render_format_codec`	—	获取当前格式/编解码器
`resolve_set_render_format_codec`	`format`, `codec`	设置渲染格式和编解码器
`resolve_get_render_mode`	—	获取渲染模式
`resolve_set_render_mode`	`renderMode`	设置渲染模式
`resolve_get_render_resolutions`	`format`, `codec`	列出渲染分辨率
`resolve_get_render_preset_list`	—	列出渲染预设
`resolve_load_render_preset`	`presetName`	加载渲染预设
`resolve_save_as_new_render_preset`	`presetName`	保存新的渲染预设
`resolve_delete_render_preset`	`presetName`	删除渲染预设
`resolve_set_render_settings`	`settings`	设置渲染设置（TargetDir、CustomName 等）
`resolve_add_render_job`	—	添加渲染任务
`resolve_delete_render_job`	`jobId`	删除渲染任务
`resolve_delete_all_render_jobs`	—	删除所有渲染任务
`resolve_get_render_job_list`	—	列出渲染任务
`resolve_start_rendering`	`jobIds?`, `isInteractiveMode?`	开始渲染
`resolve_stop_rendering`	—	停止渲染
`resolve_is_rendering_in_progress`	—	检查是否正在渲染
`resolve_get_render_status`	`jobId`	获取渲染任务状态
`resolve_render_with_quick_export`	`presetName`	快速导出
`resolve_render`	`settings?`	添加任务并开始渲染

语音与字幕（1 个工具）

工具	参数	描述
`resolve_generate_speech`	`text`, `voice?`	生成 AI 语音音频

特殊（1 个工具）

工具	参数	描述
`resolve_create_hand_animation`	`imagePath`, `...`	创建手绘动画（Daniel Batal 技法）

故障排除

Bridge 无法启动

确保 DaVinci Resolve 正在运行且已打开项目
检查控制台（工作区 → 控制台）中的错误消息
重启 DaVinci Resolve——它只在启动时扫描 Scripts 文件夹

“无法连接到 Resolve Bridge”

确保你已在 Resolve 中运行 工作区 → 脚本 → Bridge-Connection-Script
检查控制台是否显示 [Resolve Bridge] HTTP server running on http://127.0.0.1:8787
如果端口已被占用，请关闭 Resolve 并重新打开（过期的 fuscript.exe 进程可能占用端口）

工具返回错误

先调用 resolve_status 验证连接
某些操作需要打开项目、存在时间线或选中片段
Bridge 返回的错误消息会指出缺少什么

技术细节

Bridge 端口： 127.0.0.1:8787（仅限本机，无外部访问）
传输方式： HTTP/1.0，使用 Connection: close
MCP 传输方式： stdio
依赖项： mcp、requests（仅 MCP 服务器；Bridge 使用纯标准库）
Resolve 版本： 18.5+（已在 21.0.4.5 上测试）
Python： MCP 服务器需要 3.10+；Bridge 使用 Resolve 内置的 Python

许可证

MIT 许可证——参见 LICENSE 文件。

致谢

由 The Geek Gods 创建。灵感来自 DaVinci Resolve 脚本社区。

Available Tools

1 tool

resolve_healthA

Check if DaVinci Resolve bridge is running. The bridge script must be running inside Resolve via Workspace > Scripts > DaVinciResolveBridge. If this returns an error, the bridge is not running.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the error behavior: 'If this returns an error, the bridge is not running.' This is key behavioral information. However, it does not disclose what a successful response contains or whether the tool has any side effects, though 'check' implies a read-only operation. Still, the error semantics are clearly and usefully disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each earning its place. The first sentence states the purpose, the second gives the setup prerequisite, and the third explains error interpretation. It is front-loaded with the core function and contains no filler or redundant phrases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with no parameters, no output schema, and no siblings. The description covers what the tool checks and how to interpret an error. A minor gap is that it does not explicitly describe the success response, but for a health-check tool, the error condition is the most critical information. The description is otherwise complete for an agent to select and invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

This tool has zero parameters, so there is nothing to document. According to the guidelines, a baseline of 4 is appropriate when no parameters exist. The description does not need to add parameter-level detail, and it doesn't waste space on it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool does: 'Check if DaVinci Resolve bridge is running.' The verb 'check' and resource 'DaVinci Resolve bridge' are specific and unambiguous. Since there are no sibling tools, there is no need for differentiation, and the description is fully self-contained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context by explaining the prerequisite: the bridge script must be running inside Resolve via Workspace > Scripts > DaVinciResolveBridge. It also tells the agent how to interpret the result, which is effectively guidance for using the tool. There are no alternatives to contrast, so no exclusions are necessary, but it doesn't explicitly say 'use this when you need to verify connectivity.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updatev1.2.5Sep 6, 2026
- First observedresolve_health

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored 2026-09-06 05:40 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion or overlapping purposes. The tool's purpose is unambiguous.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (resolve_health), which is consistent and descriptive. With only one tool, naming consistency is inherently strong.

Tool Count2/5

A single health-check tool is far too few for a server presumably meant to bridge to DaVinci Resolve. Even as a minimal health-only server, one tool feels extremely thin and provides little value beyond a ping.

Completeness1/5

The server only provides a health check, with no ability to interact with DaVinci Resolve projects, timelines, renders, or any other meaningful operations. This is a severely incomplete surface for a bridge to a complex application.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

arsaze-mcp A
io.github.AnrosPrac
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
Image & Video Processing Multimedia Processing
241
ViewMax MCP A
io.github.bytevirts
Remote MCP for AI video, image, music and speech generation.
Audio Processing Image & Video Processing Speech Processing
141
CueFrameOAuth
ai.cueframe
Compose, edit and render video with your AI agent. Turn footage into finished edits with content-aware reframing, word-timed captions and motion graphics. Hosted MCP with OAuth sign-in; cloud processing uses credits.
Image & Video Processing Multimedia Processing
722
MaxVideoAI AOAuth
com.maxvideoai
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
AI & Machine Learning Image & Video Processing
161

Related MCP Servers

resolve-mcp
Multimedia Processing Image & Video Processing
jenkinsm13
A
license
Not graded
quality
F
maintenance
Comprehensive MCP server for DaVinci Resolve with 295+ tools to control projects, timelines, editing, color grading, rendering, and more via natural language.
Updated 6 months ago (2026-04-18 00:51 UTC)
83 PyPI
6
MIT
davinci-resolve-mcp
Multimedia Processing Audio Processing
lordhoell
A
license
Not graded
quality
D
maintenance
An MCP server that exposes the complete DaVinci Resolve scripting API, enabling AI assistants to control DaVinci Resolve programmatically with over 440 tools for project management, timeline editing, color grading, rendering, and more.
Updated 6 months ago (2026-04-03 02:08 UTC)
13
MIT
davinci-resolve-mcp-free
Multimedia Processing Image & Video Processing
MDizzleZA
A
license
Not graded
quality
C
maintenance
Enables AI assistants to control DaVinci Resolve (Free and Studio) through natural language, providing 162 tools for timeline editing, color grading, rendering, and more. Includes local AI replacements for Studio-only features like voice isolation, background removal, and transcription.
Updated 2 months ago (2026-08-16 15:40 UTC)
MIT
davinci-resolve-mcp
Multimedia Processing Image & Video Processing Audio Processing
realmikeshu
A
license
Not graded
quality
Not graded
maintenance
Enables AI assistants to control DaVinci Resolve Studio via MCP, providing full scripting API coverage plus workflow helpers for editing, media organization, rendering, grading, and more.
Updated 2 months ago (2026-08-17 16:47 UTC)
5,556 npm
MIT

Davinc-Resolve-Local-Bridge-MCP

这是什么？

工作原理

快速开始

前置要求

第 1 步 — 安装桥接脚本

第 2 步 — 安装 MCP 服务器依赖

第 3 步 — 配置你的 AI 助手

Claude Desktop

Cursor

Devin

Claude Code

任意 MCP 客户端（通用）

第 4 步 — 在 DaVinci Resolve 中启动桥接器

第 5 步 — 开始使用

架构

桥接脚本（bridge/Bridge-Connection-Script.py）

MCP 服务器（mcp_server/server.py）

全部 215 个工具

Resolve 应用程序（15 个工具）

项目管理器（18 个工具）

项目设置（7 个工具）

媒体存储（4 个工具）

媒体池（13 个工具）

时间线（21 个工具）

时间线轨道（11个工具）

时间线片段（66个工具）

Fusion 合成（14 个工具）

Fusion 工具（11 个工具）

画廊（4 个工具）

调色 / 节点（7 个工具）

渲染（22 个工具）

语音与字幕（1 个工具）

特殊（1 个工具）

故障排除

Bridge 无法启动

“无法连接到 Resolve Bridge”

工具返回错误

技术细节

许可证

致谢

Available Tools

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

resolve-mcp

davinci-resolve-mcp

davinci-resolve-mcp-free

davinci-resolve-mcp

桥接脚本（`bridge/Bridge-Connection-Script.py`）

MCP 服务器（`mcp_server/server.py`）