nodetool
Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.
- License 许可
- AGPL-3.0
- 最近更新
- 2026-11-15
- Stars
- ★ 635
- Forks
- 91
01 前言 Front Matter
- name
- nodetool
- description
- Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.
03 SKILL.md 正文
NodeTool
The NodeTool MCP server exposes one action tool, execute_code, plus a few
direct tools. Write JavaScript for execute_code. The code runs in a sandbox
and reaches NodeTool through the nodetool.* object model.
Find what exists first
- Call
nodetool.searchTools("query")inside an action to find a capability. - Read the
nodetool://capabilitiesresource for the tool list andnodetool://sandboxfor the guest surface. - Search the node registry (
search_nodes,get_node_info) before naming a node type. Never guess a type or a property name.
Build and run a workflow
create_workflowwith the graph, orget_example_workflowto start from a shipped example.validate_workflowafter every edit. It is a static check and returns in under a second. It catches unknown node types, missing required properties, unselected models, and dangling or mistyped edges.run_workflowfor a short run, orstart_background_jobfor a long one. Pollget_jobuntil it settles. The settled job carriesoutputs.get_job_logscarries the log tail and any node error. Inspect that same job. Do not start another run to read its result.
Debug a failed run
debug_workflow starts a new execution. It does not inspect the job from step
3. Call it only when a second run is intended and the user has authorized it,
because a rerun can repeat charges and side effects. After an ordinary run,
use get_job and get_job_logs first.
Rules
- Validate before running. A run can cost money.
- Start one execution per request. Never run a workflow and then debug-run it to read the result.
- Ask before deleting a workflow, asset, collection, or version.
- Report the job status and the real error text when a run fails. Do not retry blindly.
- Media generations are tracked. Pass
background: trueto get ageneration_idearly, then useawait_generation. - Resource ids may be shortened to 12 characters in results. Pass back the form you were given.
04 同仓库更多 Skills
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler.
wan-2-6-prompting
Prompt Alibaba's Wan 2.6 video — text-to-video with a global style line plus timing-bracketed shots, and image-to-video that describes only what changes over time. Covers the shot-mode switch per provider, the prompt budget, negative prompts, motion intensity wording, audio input and prompt expansion. Use whenever the model id names a Wan 2.6 video route (alibaba/wan-2.6/text-to-video, alibaba/wan-2.6/image-to-video, wan-video/wan-2.6-t2v, wan-video/wan-2.6-i2v, wan-video/wan2.6-i2v-flash) on generate_video, animate_image or a TextToVideo node. Not for Wan 2.5 or 2.7, or the Wan 2.6 image routes.
video-workflow
Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.
video-clone
Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.
video-audio-continuity
Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio and the mix of what came back. Use when a piece has more than one scene and the video model writes its own audio (Seedance 2, Veo 3, MiniMax H3, Kling 2.6 and later), or when a cut's sound drops out at the shot changes.
veo-3-prompting
Prompt Google's Veo 3 video line — the five-element shot/setting/subject/action/dialogue structure, the cinematography vocabulary it reads directly, duration and aspect-ratio tradeoffs, the audio and auto-fix switches per provider, and the fixes for visual drift, temporal inconsistency and audio mismatch. Use whenever the model id contains veo3 or veo-3 (fal-ai/veo3.1 and its fast, lite, image-to-video, first-last-frame and reference-to-video routes, fal-ai/veo3/image-to-video, google/veo3.1 on atlascloud, google/veo-3 and google/veo-3.1 on replicate, kie's veo-3-1, and Gemini's own veo-3.1-generate-preview) on generate_video, animate_image, generate_video_from_references or a TextToVideo node.