get_workflow
Read, list, analyze, strip, slice, or query saved ComfyUI workflow JSON files on disk or in the user library, and extract workflows embedded in generated PNGs.
Instructions
Return, list, summarize or query a SAVED workflow FILE — files on disk, named from the library or given as a path/JSON — NOT the graph open on the user's canvas (that is panel_graph_outline). Every action here is READ-ONLY; saving and locking are save_workflow. Driven by the action parameter:
action:"get" — the full JSON of one saved workflow FILE named from the library. Defaults to converted API format; pass format:'ui' for the raw on-disk UI JSON. Use action:"analyze" instead if you just need to UNDERSTAND the workflow — it returns a structured summary without flooding context with JSON. Use action:"get" only when you need the actual JSON for enqueue_workflow, create_workflow (action:"modify"), or save_workflow.
action:"list" — the workflows saved in the connected ComfyUI server's user library (the same ones visible in the ComfyUI web UI), INCLUDING the ones filed in subfolders. Requires a running ComfyUI server. Takes no other parameters. Returns a numbered list of library names, each relative to the library root — a workflow in a folder appears as 'VIDEO/MiniMaxH3/clip.json', and that whole string is what
filenametakes. It never reports an absence it did not establish: a listing it could not read says so, and an EMPTY listing says the library could not be CONFIRMED empty (an answer with no names in it cannot show whether it covered subfolders) and tells you to check the ComfyUI sidebar rather than recreate anything.action:"strip" — strip a workflow to a clean, flat API graph, resolving Get/Set buses, Reroutes, subgraph definitions, and bypassed/muted nodes into real connections (the 'de-getter-setter' pass). Unlike action:"get" this reads from ANY file path on disk when the connected ComfyUI is THIS machine (not just the workflow library); against a REMOTE or Cloud ComfyUI this process is not on that filesystem, so an absolute path is proxied only when it sits under user/default/workflows, user/workflows or models/workflows, and any other remote absolute path is refused rather than resolved against the local disk of this MCP process, so it loads ad-hoc / expert workflow files that action:"list" and panel_open_workflow can't resolve. Provide exactly one of: path, filename, or graph. Returns conversion warnings, a node-type summary, and the stripped graph (much smaller than the raw UI JSON).
action:"slice" — slice ONE pipeline out of a toggle-template workflow, the kind built with rgthree 'Fast Groups Bypasser/Muter' where one graph holds many pipelines and only one is active at a time. Seeds from the output/SaveImage nodes in the named
groups, takes their backward dependency closure (through real links AND virtual Set/Get buses), un-bypasses the kept nodes (and the internals of any subgraph defs they use), and returns a STANDALONE, activated UI graph carrying only the subgraph defs it uses. Pair with action:"strip" afterward to flatten the Set/Get buses into real connections.action:"from_image" — extract embedded ComfyUI workflow metadata from a PNG file. ComfyUI stores the full workflow (API format) and prompt data in PNG tEXt chunks. Use this to reverse-engineer how any ComfyUI image was generated.
action:"analyze" — SUMMARIZE a saved workflow file named from the library: sections, node settings, connections, and data flow. Returns a concise text summary (not raw JSON) optimized for AI reasoning. Prefer this over action:"get" unless you need the raw JSON for enqueue_workflow or create_workflow (action:"modify").
action:"query" — filter, traverse, project, and aggregate over a saved workflow's nodes WITHOUT dumping the whole JSON (the missing middle between action:"analyze"'s fixed summary and action:"get"'s full dump; on 100+-node graphs this is the ONLY context-safe way to answer questions like 'which KSamplers run cfg>7', 'what feeds node 42', 'count nodes by type'). Provide exactly one of path/filename/graph, then combine:
types,title,wherewidget predicates ANDed ('cfg>7', 'steps<=20', 'sampler_name=euler', 'text~sunset' — ops = != >= <= > < ~contains),ids,upstream_of/downstream_of+depth,fields,group_by,limit,max_chars. Output is TOKEN-BOUNDED and, when it truncates, the tail names WHICH of the two caps fired and the exact parameter to raise — read it and retry rather than concluding the graph can't be read. For the LIVE canvas this is panel_query_graph instead.action:"prompt_director" — read Prompt Director's latest sanitized RUNTIME state after its nodes execute: each node id, node kind, resolved Model Explorer model/LoRA context, structured edit plan, source analysis, exact final prompt, warnings, or Result Critic verdict. Secrets and image tensors are redacted. Pair it with a live panel graph audit: graph inspection explains wiring and widget state, while this explains what the nodes actually resolved and compiled. Pass
node_idto inspect one executed Prompt Director node.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ids | No | action:"query" — Keep exactly these node ids. | |
| path | No | action:"strip" / "slice" / "query" — Absolute path to a workflow .json on the connected ComfyUI host (e.g. C:\\Users\\you\\ComfyUI\\user\\default\\workflows\\pusa_extend.json). LOCAL ComfyUI: read from this host's disk — no library lookup. If a userdata path is missing the `workflows` segment after `user/default`, it is retried with that segment restored, preserving the filename exactly. REMOTE ComfyUI: not opened on this MCP host (a POSIX path is not Win32-resolved). A path under user/default/workflows, user/workflows, or models/workflows is fetched from that server's userdata library; any other remote absolute path is refused. | |
| view | No | action:"analyze" — summary (default): structured text with sections, node IDs, key settings, virtual wires, and full connection graph — best for AI understanding. overview: mermaid diagram showing sections as summary nodes with cross-section data flow. detail: mermaid diagram for one section (requires section parameter). list: text listing of all sections with data flow summary. flat: single mermaid flowchart of the entire workflow (best for small workflows). health: graph-health heuristics (disconnected nodes, duplicate model loads, orphaned branches, muted/bypassed, a sampler running denoise below 1.0 on an empty latent, an image-edit graph whose sampled canvas is not derived from the reference). | summary |
| depth | No | action:"query" — Max hops from the traversal seed (seed=0). Absent = full closure. | |
| graph | No | action:"strip" / "slice" / "query" — Inline workflow JSON (UI format for "strip"/"slice"; UI or API for "query"), as an alternative to path/filename. | |
| limit | No | action:"query" — Max nodes listed (default 40, max 200). | |
| title | No | action:"query" — Keep nodes whose title contains this. | |
| types | No | action:"query" — Keep nodes whose class_type contains ANY of these (case-insensitive). | |
| where | No | action:"query" — Widget predicates, ANDed: 'cfg>7', 'sampler_name=euler', 'text~sunset'. | |
| action | Yes | Which read to perform. "list" and "prompt_director" take no required parameters; "get" and "analyze" require `filename`; "strip", "slice" and "query" require exactly one of `path`/`filename`/`graph` (and "slice" also requires `groups`); "from_image" requires `image_path`. | |
| fields | No | action:"query" — Projection: compact one-liners (default), bare ids, or detail JSON rows. | |
| format | No | action:"get" — 'api' (default, recommended) converts to compact API format with named inputs, connection references, and _meta.mode flags for muted/bypassed nodes; 'ui' returns the raw UI format with layout positions and links arrays. action:"strip" — 'api' (default) strips to the flat resolved graph; 'raw' returns the file/graph unchanged. Each action accepts only its own two values (this field is the union of what the two tools it replaces accepted) and refuses the third rather than guessing at an alias. | api |
| groups | No | action:"slice" (REQUIRED) — Group-title substrings (case-insensitive) whose output nodes seed the slice — CSV string or array, e.g. 'TEXT TO IMAGE,TXT' or ['extend','sampler']. Shared post-proc is pulled in via the closure. | |
| node_id | No | action:"prompt_director" — Optional ComfyUI node id; omit to list all recent Prompt Director runtime states. | |
| section | No | action:"analyze" — Section name for detail view. Use view='list' first to see available section names. | |
| filename | No | Workflow library name, exactly as action:"list" reports it. A workflow filed in a folder keeps its folder in the name ('VIDEO/MiniMaxH3/clip.json') and that whole string goes here. An absolute path under the live ComfyUI workspace (e.g. a JSON in data/_downloads) is read from disk, not the user library. REQUIRED for action:"get" and action:"analyze"; one of the three sources for "strip", "slice" and "query". | |
| group_by | No | action:"query" — Aggregate: counts per class_type instead of listing. | |
| max_chars | No | action:"query" — Output character bound (default 12000, max 60000). Raise this — not `limit` — when the truncation tail says the char budget cut the result. | |
| image_path | No | action:"from_image" (REQUIRED) — Absolute path to a ComfyUI-generated PNG file | |
| upstream_of | No | action:"query" — Scope to the dependency closure FEEDING this node id. | |
| downstream_of | No | action:"query" — Scope to the nodes CONSUMING this node id's outputs. |