ComfyUI MCP
OCI · GHCR.IO/GERMANIU/COMFYUI-MCP
MCP server that wraps ComfyUI (SDXL/Wan 2.2) for image and short-video generation.
Available components
Last scanned (7 hours ago)
Scores higher than 64% of OCI servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 19 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 795 tokens (~132/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management63
- Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (50% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (12)
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (4)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed oci/ghcr.io/germaniu/comfyui-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
comfy_health Comfy Health ~31
Estado de ComfyUI: si responde, VRAM libre/total de la GPU y tamaño de la cola.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
comfy_view_url Comfy View Url ~51
Devuelve la URL LAN de descarga directa para una imagen o video ya generado (por filename).
| Name | Type | Req | Description |
|---|---|---|---|
| filename | string | yes | – |
| img_type | string | – | – |
| subfolder | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
generate_image Generate Image ~238
Genera imágenes en la RTX 3060 (SDXL vía ComfyUI). Presets: producto (fotorrealista marketing), realista (versátil), rapido (borradores ~5s), anime (checkpoint no disponible). Devuelve filename+subfolder en Pop!_OS (pedir con comfy_view_url para la URL directa de descarga). La primera generación con un checkpoint tarda ~1 min extra por carga del modelo, más ~10-30s si hay que despertar el servicio (switch de GPU con el LLM). Prompt en inglés funciona mejor. preview=true devuelve además una miniatura JPEG (~512px) para ver el resultado; solo en clientes con visión.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect | string | – | – |
| batch | integer | – | – |
| cfg | – | – | – |
| checkpoint | – | – | – |
| detail_face | boolean | – | – |
| filename_prefix | string | – | – |
| lora | – | – | – |
| lora_strength | – | – | – |
| negative_prompt | – | – | – |
| preset | string | – | – |
| preview | boolean | – | – |
| prompt | string | yes | – |
| seed | – | – | – |
| steps | – | – | – |
No output schema declared.
No examples provided.
generate_video Generate Video ~244
Genera un clip corto (1-5s, 24fps, MP4) con Wan 2.2 en la RTX 3060. Sin image_filename es txt2video; con image_filename (una imagen ya generada, ej: mcp_00001_.png) la anima usándola como primer frame — conviene que su aspect coincida con el del video. aspect: 16:9, 9:16 o 1:1. Tarda varios minutos (más la primera vez por carga del modelo); describir la escena y el movimiento de cámara en inglés. draft=true genera a ~480p, bastante más rápido: útil para probar el prompt antes de la versión final. Devuelve filename + URL de descarga. preview=true devuelve además una miniatura JPEG del primer frame.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect | string | – | – |
| cfg | – | – | – |
| draft | boolean | – | – |
| filename_prefix | string | – | – |
| image_filename | – | – | – |
| negative_prompt | – | – | – |
| preview | boolean | – | – |
| prompt | string | yes | – |
| seconds | integer | – | – |
| seed | – | – | – |
| steps | – | – | – |
No output schema declared.
No examples provided.
img2img Img2Img ~194
Varía una imagen ya generada usando img2img. Pasar image_filename (ej: test_00001_.png) y denoise (0.0=idéntica, 1.0=completamente nueva, 0.3-0.7 recomendado). Si prompt está vacío, hace variación visual pura. Útil para iterar un arte sin partir de cero o generar variaciones de memes. preview=true devuelve además una miniatura JPEG; solo en clientes con visión.
| Name | Type | Req | Description |
|---|---|---|---|
| cfg | – | – | – |
| checkpoint | – | – | – |
| denoise | number | – | – |
| filename_prefix | string | – | – |
| image_filename | string | yes | – |
| lora | – | – | – |
| lora_strength | – | – | – |
| negative_prompt | – | – | – |
| preset | string | – | – |
| preview | boolean | – | – |
| prompt | string | – | – |
| seed | – | – | – |
| steps | – | – | – |
No output schema declared.
No examples provided.
list_models List Models ~37
Lista checkpoints, loras y presets disponibles en ComfyUI. Si ComfyUI está dormido devuelve solo los presets, sin despertarlo.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the ComfyUI MCP server?
ComfyUI MCP runs locally as a container image, launched with docker run --rm -i -e COMFYUI_URL -e COMFYUI_PUBLIC_URL -e MCP_AUTH_TOKEN ghcr.io/germaniu/comfyui-mcp:0.1.1 --stdio. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/germaniu/comfyui-mcp
claude mcp add germaniu-comfyui-mcp -- docker run --rm -i -e COMFYUI_URL -e COMFYUI_PUBLIC_URL -e MCP_AUTH_TOKEN ghcr.io/germaniu/comfyui-mcp:0.1.1 --stdio
This image reads COMFYUI_URL, COMFYUI_PUBLIC_URL and MCP_AUTH_TOKEN. Set them in your client's env block for this server; docker run -e passes each one through to the container.
What is the ComfyUI MCP server?
ComfyUI MCP is listed in the public MCP registry as io.github.GermaniU/comfyui-mcp. MCP server that wraps ComfyUI (SDXL/Wan 2.2) for image and short-video generation. This page covers its container image (ghcr.io/germaniu/comfyui-mcp).
Is the ComfyUI MCP server safe to use?
ComfyUI MCP scores 45 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ComfyUI MCP server expose?
ComfyUI MCP exposes 6 tools: generate_image, list_models, comfy_health, comfy_view_url, img2img, generate_video. Their descriptions and schemas cost roughly 795 tokens of context every time the server is loaded.
Is the ComfyUI MCP server still maintained?
ComfyUI MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ComfyUI MCP server under?
ComfyUI MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the ComfyUI MCP server?
VerifyMCP ran 12 checks on ComfyUI MCP, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about ComfyUI MCP: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.