Conversions across 221 color spaces, tested against cited sources: CSS strings, gamut, LUTs
ComfyUI Builder is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user comfyui-builder-mcp '--' npx -y mcp-comfy-ui-builder
# 2 — ask your agent for something these tools do
# list_node_types, get_node_info, check_compatibility and 60 more
ComfyUI Builder costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts ComfyUI Builder as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user comfyui-builder-mcp '--' npx -y mcp-comfy-ui-builderReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take COMFYUI_HOST (ComfyUI API URL (e.g. http://127.0.0.1:8188). Required for execution, queue, outputs.), COMFYUI_PATH (Path to ComfyUI install. Required for install_custom_node, install_model.), COMFYUI_KNOWLEDGE_DIR (Path to knowledge directory (default: package knowledge/). Use when MCP runs from different cwd.) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
63 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List ComfyUI node types from the knowledge base. Optionally filter by category or priority.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Filter by category (e.g. loaders, sampling, image) |
| priority | string | no | Filter by priority |
Get full node information for a ComfyUI node by its class name. Uses live ComfyUI when COMFYUI_HOST is set, otherwise knowledge base.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_name | string | yes | Node class name (e.g. KSampler, CheckpointLoaderSimple) |
Check if output of one node can connect to input of another (using node-compatibility.json).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from_node | string | yes | Source node class name |
| to_node | string | yes | Target node class name |
Suggest ComfyUI nodes for a task (search by description/use_cases) or by output type they produce.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_description | string | no | Short task description (e.g. "load checkpoint", "decode latent") |
| input_type | string | no | Output type to match (e.g. MODEL, IMAGE, LATENT) |
Get all node definitions from the running ComfyUI instance (GET /object_info). Returns class names and categories. Requires ComfyUI to be running at COMFYUI_HOST.
No parameter schema on file.
Search nodes by query string and optional filters (category, input_type, output_type). Searches both live ComfyUI and knowledge base; live overrides KB for same class.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Search in class name, display name, description, category |
| category | string | no | Filter by category (e.g. loaders, sampling) |
| input_type | string | no | Filter by input type (e.g. MODEL, IMAGE) |
| output_type | string | no | Filter by output type (e.g. LATENT, IMAGE) |
Get detailed input definitions for a node (required and optional). Uses live ComfyUI if available, otherwise knowledge base.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_name | string | yes | Node class name (e.g. KSampler, CheckpointLoaderSimple) |
Get output types and names for a node. Uses live ComfyUI if available, otherwise knowledge base.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_name | string | yes | Node class name (e.g. KSampler, CheckpointLoaderSimple) |
List all node categories from live ComfyUI and knowledge base (merged, unique).
No parameter schema on file.
Sync node definitions from running ComfyUI to the knowledge base. Adds only nodes that are not already in base-nodes.json. Creates knowledge/ if missing (or set COMFYUI_KNOWLEDGE_DIR to point to the knowledge directory). Requires ComfyUI to be running.
No parameter schema on file.
List available workflow template ids (e.g. txt2img). No ComfyUI connection needed.
No parameter schema on file.
Build a ComfyUI workflow from a template and parameters. Returns workflow JSON ready to execute or save. For txt2img_flux, call get_system_resources first and use only when flux_ready is true (FLUX needs ~12GB+ VRAM).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| template | string | yes | Template id (e.g. txt2img, txt2img_flux). Use list_templates to see available. |
| params | object | no | Optional: width, height, steps, cfg, prompt, negative_prompt, seed, ckpt_name, filename_prefix, batch_size, denoise; for txt2img_flux: clip_l, t5xxl, guidance |
Build a workflow that takes your image and outputs another image in a chosen style (cartoon, oil painting, anime, etc.). Returns workflow JSON plus a recipe (prompt and params) so you can run it or regenerate with the same settings. Image must be in ComfyUI input folder (upload first if needed).…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| image | string | yes | Input image filename in ComfyUI input folder (e.g. from upload or prepare_image_for_workflow) |
| style | string | yes | Style: keyword (cartoon, oil_painting, anime, watercolor, sketch, comic, pixel_art, pastel, cyberpunk) or free text prompt |
| prompt | string | no | Override prompt (if set, style keyword is ignored) |
| negative_prompt | string | no | Negative prompt |
| denoise | number | no | Strength of style change (default 0.65, lower = closer to original) |
| steps | integer | no | — |
| cfg | number | no | — |
| seed | integer | no | — |
| ckpt_name | string | no | Checkpoint filename |
| filename_prefix | string | no | SaveImage prefix |
Suggest workflow template (txt2img_flux or txt2img) from checkpoint filename. FLUX checkpoints (e.g. flux1-dev-fp8.safetensors) use txt2img_flux; SD XL / SD 1.5 use txt2img. Call before build_workflow when the user did not specify a template.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ckpt_name | string | yes | Checkpoint filename (e.g. flux1-dev-fp8.safetensors, sd_xl_base_1.0.safetensors) |
Create a new empty workflow context. Returns workflow_id to use with add_node, connect_nodes, get_workflow_json, validate_workflow, finalize_workflow, execute_workflow.
No parameter schema on file.
Add a node to a dynamic workflow. Returns the new node id (e.g. "1", "2").
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
| class_type | string | yes | ComfyUI node class (e.g. CheckpointLoaderSimple, CLIPTextEncode) |
| inputs | object | no | Node inputs (literal values; use connect_nodes for links) |
Connect an output of one node to an input of another in a dynamic workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
| from_node | string | yes | Source node id (e.g. "1") |
| output_idx | integer | yes | Output index (usually 0) |
| to_node | string | yes | Target node id |
| input_name | string | yes | Target input name (e.g. model, clip, positive) |
Remove a node from a dynamic workflow. Does not fix references (validation will report dangling refs).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
| node_id | string | yes | Node id to remove |
Set a literal input on a node in a dynamic workflow (overwrites existing value or link).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
| node_id | string | yes | Node id |
| input_name | string | yes | Input name (e.g. text, ckpt_name, seed) |
| value | yes | Value (string, number, boolean, or [nodeId, outputIndex] for links) |
Get the current workflow JSON for a dynamic workflow (for execute_workflow or save_workflow).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
Validate a dynamic workflow: checks that all node references exist and output indices are valid.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
Get the workflow JSON for a dynamic workflow (same as get_workflow_json). Use with execute_workflow or save_workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
Submit a ComfyUI workflow to run. Returns prompt_id. Use get_execution_status(prompt_id) to check result. Requires COMFYUI_HOST and ComfyUI running.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string (from build_workflow or loaded file) |
Submit a ComfyUI workflow and wait until execution completes with real-time progress (WebSocket if available, polling fallback). Returns prompt_id, status (completed/failed/timeout), and outputs. When status is error, still check outputs — if present, use download_output or get_last_output to…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string (from build_workflow or loaded file) |
| timeout_ms | integer | no | Max wait in milliseconds. When omitted, uses get_system_resources recommended_timeout_ms (e.g. 1.2M on MPS). |
| stream_progress | boolean | no | Stream progress updates via WebSocket (default true) |
Get execution status and outputs for a prompt. Returns status, image filenames, and view URLs. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id returned by execute_workflow |
Get full error details for a prompt (node_id, exception_type, exception_message, full traceback). Use when execute_workflow_sync failed or get_execution_status shows errors. Returns structured errors from ComfyUI history status.messages. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id from execute_workflow or execute_workflow_sync |
Get real-time execution progress for a prompt (WebSocket if available, polling fallback). Returns status, current_node, progress%, queue_position, and outputs. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id returned by execute_workflow or execute_workflow_sync |
Execute workflow with streaming real-time progress updates. Requires WebSocket support. Returns result and progress event history. Use for monitoring execution progress. Requires COMFYUI_HOST and WebSocket connection.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string (from build_workflow or loaded file) |
| timeout_ms | integer | no | Max wait in milliseconds (default 300000) |
Execute multiple workflows in batch. Submits each workflow and waits for completion (polling). Optional concurrency and stop_on_error. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflows | array | yes | Array of workflow JSON strings |
| concurrency | integer | no | Max workflows running at once (default 1) |
| stop_on_error | boolean | no | Stop batch on first failure (default false) |
| timeout_ms | integer | no | Per-workflow timeout in ms (default 300000) |
Get ComfyUI execution history (GET /history) without prompt_id. Returns last N prompts with prompt_id, status, outputs (filenames), elapsed. Use when execute_workflow_sync did not return prompt_id (e.g. WebSocket timeout) to find the latest run and its outputs. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Number of recent history entries (default 5) |
Get info for the most recent prompt that has image output (skips failed prompts). Use when prompt_id was lost (e.g. execute_workflow_sync timed out). Returns prompt_id, filename, subfolder, view_url. Then use download_by_filename to save the file. Requires COMFYUI_HOST.
No parameter schema on file.
List all output files (images, gifs) for a completed prompt. Returns prompt_id, node_id, type, filename, url. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id from execute_workflow or execute_workflow_sync |
Download a single output file to a local path. Use list_outputs to get file info. Use output_format to convert to png, jpeg, or webp. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id |
| node_id | string | yes | Node id (from list_outputs) |
| filename | string | yes | Filename (from list_outputs) |
| dest_path | string | yes | Local path to save the file |
| subfolder | string | no | Subfolder (from list_outputs) |
| output_format | string | no | Convert image to this format (png, jpeg, or webp) |
| convert_quality | number | no | Quality for jpeg/webp (default 85) |
Download an output file by filename (no prompt_id needed). Uses GET /view. Use when you have filename from get_history or get_last_output. If return_base64 is true, file is not written to disk; returns base64 data. When size > 800 KB, automatically converts to WebP to stay under 1MB base64 limits.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filename | string | yes | Output filename (e.g. from get_last_output or get_history) |
| dest_path | string | yes | Local path to save the file (ignored when return_base64 is true) |
| subfolder | string | no | Subfolder (default empty) |
| type | string | no | View type (default "output") |
| return_base64 | boolean | no | If true, return file as base64 (auto WebP when > 800 KB) |
| max_base64_bytes | integer | no | When return_base64 and file size > this, convert to WebP (default 819200). Set 0 to disable. |
| convert_quality | number | no | WebP/JPEG quality when converting (default 85) |
| output_format | string | no | Convert image to this format (png, jpeg, or webp) before saving or returning base64 |
Download all output files for a prompt into a directory. Returns list of saved paths. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id from execute_workflow or execute_workflow_sync |
| dest_dir | string | yes | Local directory path to save files |
| prefix_node_id | boolean | no | Prefix filename with node_id to avoid collisions (default true) |
List models available on the ComfyUI server (from object_info). Optionally filter by type: checkpoint, lora, vae, controlnet, upscale, embedding, clip. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by model type (omit for all types) |
Get info for a model by name and type. Returns name, type, path; null if not found. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Model filename (e.g. sd_xl_base_1.0.safetensors) |
| type | string | yes | Model type: checkpoint, lora, vae, controlnet, upscale, embedding, clip |
Check if a model exists on the ComfyUI server (in object_info model lists). Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Model filename |
| type | string | yes | Model type |
Extract required models from a workflow (loader nodes: CheckpointLoaderSimple, LoraLoader, VAELoader, ControlNetLoader, UpscaleModelLoader, etc.). Returns list of { name, type, nodeId, nodeClass, inputName }. No ComfyUI connection needed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string |
Check which models required by a workflow exist on the ComfyUI server. Returns ready (boolean), missing, and found lists. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string |
Get ComfyUI station resources (GPU/VRAM/RAM) and recommendations for model size, resolution, and batch size. Returns flux_ready (desktop FLUX needs ~12GB+ VRAM) and platform_hints (e.g. Apple Silicon: M-Flux as quantized/MLX variant — different model or FLUX via custom nodes). Call this first…
No parameter schema on file.
Get recommendations for image generation: system resources (max resolution, model size, batch) and, if the user prompt suggests text/letters in the image, advice on models and settings. Many base models (SD 1.5, SD XL) render text poorly; FLUX, SD 3, or checkpoints trained for text work better.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | no | User's image description or goal (e.g. "a sign that says Hello"). If it suggests text/letters in the image, recommendations will include model and setting advice for legible text. |
Create a parameterized workflow template from a workflow and parameter definitions. Returns template JSON for use with apply_template or validate_template_params. Parameters bind to node inputs via nodeBindings (nodeId, inputName).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | Workflow JSON string |
| params | array | yes | Parameter definitions with nodeBindings |
| name | string | no | Template name |
| description | string | no | Template description |
| category | string | no | Template category |
Apply parameter values to a workflow template. Returns workflow JSON ready to execute or save. Use create_template to build a template, then apply_template with values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| template | string | yes | Template JSON string (from create_template) |
| values | object | yes | Parameter values (e.g. { prompt: "a cat", seed: 42 }) |
Validate that parameter values satisfy a workflow template (required params, types).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| template | string | yes | Template JSON string |
| values | object | yes | Parameter values |
List available workflow macros (built-in sub-workflows). Returns id, name, description, inputs, outputs.
No parameter schema on file.
Insert a macro (sub-workflow) into a dynamic workflow. Connects macro input ports to existing nodes. Returns nodeIdMap and outputPorts so you can connect macro outputs. Use workflow_id from create_workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow_id | string | yes | Workflow id from create_workflow |
| macro_id | string | yes | Macro id (e.g. upscale_refine). Use list_macros to see available. |
| input_connections | object | yes | Map port name -> [source node id, output index] for links, or literal (e.g. filename for LoadImage) |
Execute a chain of workflows in sequence. Each step runs after the previous completes. Use inputFrom and outputTo to pass the output image from one step to the next (e.g. txt2img → upscale → img2img). Steps can use workflow JSON or saved workflow name. Prefer saved workflow name (string) for large…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| steps | array | yes | Chain steps |
| timeout_ms | integer | no | Per-step timeout (default 300000) |
| stop_on_error | boolean | no | Stop chain on first failure (default false) |
List loaded plugins (from plugins/*/plugin.json) and counts of macros/templates contributed by each.
No parameter schema on file.
Reload plugins from plugins/*/plugin.json and refresh macro registry.
No parameter schema on file.
Restart ComfyUI so that newly installed custom nodes are loaded, then optionally sync them to the knowledge base. Requires COMFYUI_PATH (ComfyUI installation directory) and uses COMFYUI_HOST for the port. Kills the process on the ComfyUI port and starts main.py from COMFYUI_PATH. After restart,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wait_for_ready | boolean | no | Wait for ComfyUI to respond before returning. Default true. |
| sync_after_restart | boolean | no | After restart, run sync_nodes_to_knowledge to update the knowledge base with custom nodes. Default true when wait_for_ready is true. |
| wait_timeout_ms | number | no | Max ms to wait for ComfyUI ready. Default 120000. |
Fetch the first output image from a completed prompt and upload it to ComfyUI input folder. Returns the filename to use in LoadImage for a follow-up workflow (e.g. image caption / verification). Use after get_execution_status confirms the prompt finished with image output. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | yes | Prompt id from execute_workflow (run must be completed with image output) |
List current ComfyUI queue (running and pending prompts). Requires COMFYUI_HOST.
No parameter schema on file.
Stop the currently running workflow on ComfyUI. Optionally pass prompt_id to interrupt only that prompt. If cleanup_after_ms is set (and prompt_id given), after interrupt the tool will poll the queue and remove the prompt from queue if it is still there (frees GPU for next job). Requires…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_id | string | no | Optional: interrupt only this prompt if it is running; omit to interrupt current run |
| cleanup_after_ms | integer | no | If set (and prompt_id given), after interrupt poll queue and remove prompt if still running (e.g. 5000). Helps free GPU after FLUX/interrupt. |
Clear ComfyUI queue: remove all pending and stop/clear running. Requires COMFYUI_HOST.
No parameter schema on file.
Remove specific items from ComfyUI queue by prompt_id. Use list_queue to get prompt_ids. Requires COMFYUI_HOST.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt_ids | array | yes | List of prompt_id to remove from queue (from list_queue or execute_workflow) |
Install one or more custom nodes via ComfyUI-Manager cm-cli (e.g. ComfyUI-Blip, WAS-Node-Suite). Requires COMFYUI_PATH and ComfyUI-Manager installed in custom_nodes. ComfyUI-Manager cm-cli requires Python package "rich" (pip install rich in your ComfyUI Python environment). Restart ComfyUI after…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node_names | array | yes | Node pack names as in ComfyUI-Manager (e.g. ComfyUI-Blip, ComfyUI-Impact-Pack) |
| channel | string | no | Optional channel (see cm-cli docs) |
| mode | string | no | Optional mode |
Download and install a model (checkpoint, LoRA, VAE, etc.) by URL. Requires COMFYUI_PATH. Uses comfy-cli if available (pip install comfy-cli), otherwise fetches the file directly. model_type: checkpoint, lora, vae, controlnet, clip, embeddings, hypernetwork, upscale_models, clip_vision, unet,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Direct download URL (e.g. from Civitai, HuggingFace) |
| model_type | string | no | Type: checkpoint, lora, vae, controlnet, clip, embeddings, hypernetwork, upscale_models, clip_vision, unet, diffusers |
Save a workflow JSON to file (workflows/<name>.json). Returns path. Use after build_workflow to persist for later load_workflow or execute_workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Name for the workflow file (alphanumeric, dash, underscore; .json added automatically) |
| workflow | string | yes | Workflow JSON string (from build_workflow or load_workflow) |
List saved workflows (names and paths) from workflows/ directory.
No parameter schema on file.
Load a saved workflow by name (from workflows/<name>.json) or by path. Returns workflow JSON for use with execute_workflow or save_workflow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name_or_path | string | yes | Workflow name (filename without .json) or full path to .json file |
No parameter schema on file.
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ComfyUI Builder or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (40 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| check_compatibility | no tags | |
| list_node_categories | no tags | |
| sync_nodes_to_knowledge | no tags | |
| list_templates | no tags | |
| create_workflow | no tags | |
| add_node | no tags | |
| remove_node | no tags | |
| get_workflow_json | no tags | |
| validate_workflow | no tags | |
| execute_batch | no tags | |
| get_history | no tags | |
| create_template | no tags | |
| list_macros | no tags | |
| insert_macro | no tags | |
| execute_chain | no tags | |
| list_plugins | no tags | |
| reload_plugins | no tags | |
| reload_comfyui | no tags | |
| prepare_image_for_workflow | untrusted-input | untrusted-input: keyword "fetch" |
| list_queue | no tags | |
| interrupt_execution | no tags | |
| clear_queue | no tags | |
| delete_queue_items | no tags | |
| install_custom_node | no tags | |
| install_model | untrusted-input | untrusted-input: keyword "download", parameter "url" with "fetches" in the description |
| save_workflow | no tags | |
| list_saved_workflows | no tags | |
| load_workflow | no tags | |
| execute_workflow | no tags | |
| get_execution | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_nodes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_node_info | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_models | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_workflow_models | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_generation_recommendations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_outputs | sensitive-sourceuntrusted-input | sensitive-source: keyword "list_files"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| download_outputs | untrusted-inputexternal-sink | untrusted-input: keyword "download"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| build_workflow | no tags | |
| set_node_input | no tags | |
| apply_template | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 3.0.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish ComfyUI Builder can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.