Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
list_api_nodesDiscover and run hosted partner/API nodes on the connected ComfyUI (e.g. Flux/BFL, Ideogram, Kling, Stability). These call external image/video providers and run server-side, requiring a Comfy account/API key configured on the ComfyUI server — they spend PAID api credits, unlike a local-GPU render.…Discover and run hosted partner/API nodes on the connected ComfyUI (e.g. Flux/BFL, Ideogram, Kling, Stability). These call external image/video providers and run server-side, requiring a Comfy account/API key configured on the ComfyUI server — they spend PAID api credits, unlike a local-GPU render.…
No input schema was published for this tool.
appsMicro-apps on this ComfyUI (panel Apps feature): named workflows packaged for one-click runs. Driven by the `action` parameter:Micro-apps on this ComfyUI (panel Apps feature): named workflows packaged for one-click runs. Driven by the `action` parameter:
No input schema was published for this tool.
batchRun MANY ComfyUI workflows under one durable batch_id. Driven by the `action` parameter:Run MANY ComfyUI workflows under one durable batch_id. Driven by the `action` parameter:
No input schema was published for this tool.
calculateEvaluate a batch of math expressions exactly — no ComfyUI connection needed, so it works even in cloud mode or when ComfyUI is down. A safe, zero-dependency expression evaluator (no eval): numbers only, no strings/arrays/property access. Handy for the arithmetic agents get wrong token-by-token.Evaluate a batch of math expressions exactly — no ComfyUI connection needed, so it works even in cloud mode or when ComfyUI is down. A safe, zero-dependency expression evaluator (no eval): numbers only, no strings/arrays/property access. Handy for the arithmetic agents get wrong token-by-token.
No input schema was published for this tool.
comfy_cliDrive the official comfy-cli (envelope/1 JSON contract) for the selected ComfyUI environment. The MCP resolves `comfy` from COMFY_CLI_PATH, PATH, or the selected workspace's .venv/venv. Driven by the `action` parameter:Drive the official comfy-cli (envelope/1 JSON contract) for the selected ComfyUI environment. The MCP resolves `comfy` from COMFY_CLI_PATH, PATH, or the selected workspace's .venv/venv. Driven by the `action` parameter:
No input schema was published for this tool.
get_defaultsRead and write settings — either OUR generation defaults or ComfyUI's own frontend UI settings. These are two SEPARATE stores and the `action` says which one you mean:Read and write settings — either OUR generation defaults or ComfyUI's own frontend UI settings. These are two SEPARATE stores and the `action` says which one you mean:
No input schema was published for this tool.
get_historyRead what has already been generated on this machine — execution history, why a run failed, and the settings your past renders actually used. Driven by the `action` parameter:Read what has already been generated on this machine — execution history, why a run failed, and the settings your past renders actually used. Driven by the `action` parameter:
No input schema was published for this tool.
comfyui-mcpNo description publishedThis tool published no description. Forge does not invent one.
generate_imageGenerate media from a prompt or an existing image — the high-level entry points that build the graph for you. Every action enqueues on the connected ComfyUI and returns the prompt_id immediately; the resulting asset_id arrives in the completion notification. Driven by the `action` parameter:Generate media from a prompt or an existing image — the high-level entry points that build the graph for you. Every action enqueues on the connected ComfyUI and returns the prompt_id immediately; the resulting asset_id arrives in the completion notification. Driven by the `action` parameter:
No input schema was published for this tool.
get_imageFetch, browse and inspect ComfyUI images and registered assets. Driven by the `action` parameter:Fetch, browse and inspect ComfyUI images and registered assets. Driven by the `action` parameter:
No input schema was published for this tool.
upload_imageprivilegedPut a file where ComfyUI (or cloud storage) can read it. Driven by the `action` parameter:Put a file where ComfyUI (or cloud storage) can read it. Driven by the `action` parameter:
No input schema was published for this tool.
install_comfyuiprivilegedInstall, update and configure the local ComfyUI installation, its sidebar panel, and this MCP server itself. Driven by the `action` parameter:Install, update and configure the local ComfyUI installation, its sidebar panel, and this MCP server itself. Driven by the `action` parameter:
No input schema was published for this tool.
kitchenSee what comfy-kitchen can do on this GPU, find where a graph is leaving it on the table, and apply the faster path. Driven by `action`:See what comfy-kitchen can do on this GPU, find where a graph is leaving it on the table, and apply the faster path. Driven by `action`:
No input schema was published for this tool.
noopnoopnoop
No input schema was published for this tool.
apply_manifestNo description publishedThis tool published no description. Forge does not invent one.
clear_vramFree GPU VRAM by unloading cached models from ComfyUI. Use this between generation runs with different model families (e.g. switching from SDXL to Flux) or when running low on VRAM. Optionally unload only models or only memory.Free GPU VRAM by unloading cached models from ComfyUI. Use this between generation runs with different model families (e.g. switching from SDXL to Flux) or when running low on VRAM. Optionally unload only models or only memory.
No input schema was published for this tool.
model_metadataCurate a model file's embedded .safetensors metadata (Model Explorer). Driven by the `action` parameter:Curate a model file's embedded .safetensors metadata (Model Explorer). Driven by the `action` parameter:
No input schema was published for this tool.
download_modelFind model weights and get them onto the connected ComfyUI, and track the transfers. Driven by the `action` parameter:Find model weights and get them onto the connected ComfyUI, and track the transfers. Driven by the `action` parameter:
No input schema was published for this tool.
list_local_modelsInspect what models this ComfyUI has installed, and where it looks for them. Driven by the `action` parameter:Inspect what models this ComfyUI has installed, and where it looks for them. Driven by the `action` parameter:
No input schema was published for this tool.
bisectBinary-search (git-bisect style) over installed ComfyUI custom nodes to find which one causes a problem. A state machine driven by the `action` parameter:Binary-search (git-bisect style) over installed ComfyUI custom nodes to find which one causes a problem. A state machine driven by the `action` parameter:
No input schema was published for this tool.
install_custom_nodeprivilegedInstall, repair, enable/disable and remove ComfyUI custom node packs on this ComfyUI. To FIND a pack in the public registry first, use search_custom_nodes. Driven by the `action` parameter:Install, repair, enable/disable and remove ComfyUI custom node packs on this ComfyUI. To FIND a pack in the public registry first, use search_custom_nodes. Driven by the `action` parameter:
No input schema was published for this tool.
node_packNo description publishedThis tool published no description. Forge does not invent one.
node_snapshotCustom-node snapshots via ComfyUI-Manager (mirrors `comfy node save-snapshot` / `restore-snapshot`). Driven by the `action` parameter:Custom-node snapshots via ComfyUI-Manager (mirrors `comfy node save-snapshot` / `restore-snapshot`). Driven by the `action` parameter:
No input schema was published for this tool.
panel_list_toolsList the live-canvas panel tools (the user's open ComfyUI graph): names + one-line summaries. Use panel_describe_tool then panel_call_tool to run one.List the live-canvas panel tools (the user's open ComfyUI graph): names + one-line summaries. Use panel_describe_tool then panel_call_tool to run one.
No input schema was published for this tool.
panel_describe_toolFull description and JSON Schema for one panel tool.Full description and JSON Schema for one panel tool.
No input schema was published for this tool.
panel_call_toolRun a panel tool by name with args matching its panel_describe_tool schema.Run a panel tool by name with args matching its panel_describe_tool schema.
No input schema was published for this tool.
restart_comfyuiControl the lifecycle of the ComfyUI server process. Driven by the `action` parameter:Control the lifecycle of the ComfyUI server process. Driven by the `action` parameter:
No input schema was published for this tool.
queueInspect and manage the ComfyUI execution queue. Driven by the `action` parameter:Inspect and manage the ComfyUI execution queue. Driven by the `action` parameter:
No input schema was published for this tool.
search_custom_nodesDiscover ComfyUI custom node PACKS in the public ComfyUI Registry (registry.comfy.org). Read-only and network-only: queries the hosted registry over HTTP and does NOT require a running ComfyUI or COMFYUI_PATH. This searches node PACKS, not models (use download_model action:"search") and not local i…Discover ComfyUI custom node PACKS in the public ComfyUI Registry (registry.comfy.org). Read-only and network-only: queries the hosted registry over HTTP and does NOT require a running ComfyUI or COMFYUI_PATH. This searches node PACKS, not models (use download_model action:"search") and not local i…
No input schema was published for this tool.
report_issueNo description publishedThis tool published no description. Forge does not invent one.
runpodDeploy, start, stop, inspect and connect to RunPod cloud GPU pods, and switch rendering between your local machine and a pod. Driven by the `action` parameter. SPENDS MONEY: action:"create" and action:"start" put a pod into a billing state; action:"stop" ends GPU billing. Confirm with the user befo…Deploy, start, stop, inspect and connect to RunPod cloud GPU pods, and switch rendering between your local machine and a pod. Driven by the `action` parameter. SPENDS MONEY: action:"create" and action:"start" put a pod into a billing state; action:"stop" ends GPU billing. Confirm with the user befo…
No input schema was published for this tool.
runpod_watchWatch a RunPod pod's live status in the control panel, stop watching it, or diagnose why it isn't usable. Driven by the `action` parameter. None of these actions DEPLOYS or resumes a pod — the runpod tool does that. One of them CAN stop one, though: action:"watch" arms the idle auto-stop, so a watc…Watch a RunPod pod's live status in the control panel, stop watching it, or diagnose why it isn't usable. Driven by the `action` parameter. None of these actions DEPLOYS or resumes a pod — the runpod tool does that. One of them CAN stop one, though: action:"watch" arms the idle auto-stop, so a watc…
No input schema was published for this tool.
list_packsBundled ComfyUI knowledge — installer packs, model-family skills, workflow templates — plus the two workflow-readiness checks. Driven by the `action` parameter:Bundled ComfyUI knowledge — installer packs, model-family skills, workflow templates — plus the two workflow-readiness checks. Driven by the `action` parameter:
No input schema was published for this tool.
get_system_statsInspect the connected ComfyUI server: what it is running on, what it has logged, and whether it is healthy enough to dispatch work to. All three actions are READ-ONLY — nothing here mutates anything. Driven by the `action` parameter:Inspect the connected ComfyUI server: what it is running on, what it has logged, and whether it is healthy enough to dispatch work to. All three actions are READ-ONLY — nothing here mutates anything. Driven by the `action` parameter:
No input schema was published for this tool.
train_prepare_datasetStage and curate the training DATASETS a LoRA run consumes — the images and their captions. Datasets are keyed by `name`; the jobs that train on them live in the separate `train_start` tool and are keyed by `id`. Driven by the `action` parameter:Stage and curate the training DATASETS a LoRA run consumes — the images and their captions. Datasets are keyed by `name`; the jobs that train on them live in the separate `train_start` tool and are keyed by `id`. Driven by the `action` parameter:
No input schema was published for this tool.
train_startRun and inspect LoRA training JOBS — launch a run, poll it, stop it, delete it, and read back the settings behind it. Jobs are keyed by `id`; the datasets they train on live in the separate `train_prepare_dataset` tool and are keyed by `name`. Driven by the `action` parameter:Run and inspect LoRA training JOBS — launch a run, poll it, stop it, delete it, and read back the settings behind it. Jobs are keyed by `id`; the datasets they train on live in the separate `train_prepare_dataset` tool and are keyed by `name`. Driven by the `action` parameter:
No input schema was published for this tool.
train_doctorPreflight and set up the TRAINER ITSELF — the docker/GPU/venv machinery every training job needs. Touches no dataset and no job. Driven by the `action` parameter:Preflight and set up the TRAINER ITSELF — the docker/GPU/venv machinery every training job needs. Touches no dataset and no job. Driven by the `action` parameter:
No input schema was published for this tool.
33 of 37 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
67 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+55 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies, optionalDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.