Conversions across 221 color spaces, tested against cited sources: CSS strings, gamut, LUTs
ComfyUI Light 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
Workflow-first, Batch-native, Context-light.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'COMFYUI_URL=${COMFYUI_URL}' --env 'WORKFLOWS_DIR=${WORKFLOWS_DIR}' --env 'DATA_DIR=${DATA_DIR}' --env 'OUTPUT_DIR=${OUTPUT_DIR}' --transport stdio comfyui-light-mcp '--' npx -y comfyui-light-mcp
# 2 — ask your agent for something these tools do
# list_workflows, run_workflow, get_result and 1 more
It needs COMFYUI_URL, WORKFLOWS_DIR, DATA_DIR, OUTPUT_DIR: this reads them from your environment, so export them first.
ComfyUI Light 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 Light 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. Claude Code reads COMFYUI_URL (Required installation choice: your trusted running ComfyUI HTTP(S) endpoint. No credentials, query or fragment), WORKFLOWS_DIR (Required absolute existing directory containing your reviewed workflow API JSON and manifest pairs), DATA_DIR (Required absolute writable SQLite state directory. Use a separate directory per MCP process), OUTPUT_DIR (Required absolute writable output/download/index directory) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx COMFYUI_URL …, setx WORKFLOWS_DIR …, setx DATA_DIR …, setx OUTPUT_DIR … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'COMFYUI_URL=${COMFYUI_URL}' --env 'WORKFLOWS_DIR=${WORKFLOWS_DIR}' --env 'DATA_DIR=${DATA_DIR}' --env 'OUTPUT_DIR=${OUTPUT_DIR}' --transport stdio comfyui-light-mcp '--' npx -y comfyui-light-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs settings only you can give it: COMFYUI_URL — Required installation choice: your trusted running ComfyUI HTTP(S) endpoint. No credentials, query or fragment.; WORKFLOWS_DIR — Required absolute existing directory containing your reviewed workflow API JSON and manifest pairs.; DATA_DIR — Required absolute writable SQLite state directory. Use a separate directory per MCP process.; OUTPUT_DIR — Required absolute writable output/download/index directory.. You set them in your own client’s config, on your machine — this marketplace never holds it.
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.
4 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.
列出工作流(名称+描述+参数个数+ready/invalid/deleted 状态+指纹摘要+最后加载结果)。传 workflow 名则返回当前有效版本的完整参数说明;invalid 返回有界加载错误,不回退旧版本。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | no | 可选:工作流名,返回参数详情 |
提交运行工作流:单运行传 params(P2 兼容),批量传 runs 数组(每项 {label?, params})。dry_run=true 时只做只读预检,绝不创建 Batch/Job/Attempt 或提交 Prompt,返回逐项统计与 passed/failed/unknown 检查。正式运行参数只接受 manifest 白名单;批量单 run 参数错误记为 invalid job,单运行简写整体报错。可选 idempotency_key、continue_on_error(默认 true)、max_attempts(默认 1)。正式提交立即返回 batch_id,用…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | list_workflows 中的名称 |
| dry_run | boolean | no | true:只预检并返回 not_submitted;不写 SQLite、不提交 Prompt、不触发调度或生成 |
| params | object | no | 单运行参数集(与 runs 二选一) |
| runs | array | no | 批量运行数组(与 params 二选一);按数组顺序调度执行 |
| label | string | no | 单运行时的可选标记 |
| idempotency_key | string | no | 幂等键:同键+相同请求内容重复调用返回既有 batch,不重复提交;同键但内容不同返回 IDEMPOTENCY_CONFLICT |
| continue_on_error | boolean | no | 默认 true;false 时首个失败将放弃该 batch 剩余未提交任务 |
| max_attempts | integer | no | 失败重试次数上限(含首次共 N 次尝试),默认 1 不重试 |
查询结果:省略 mode 时返回 index 指定的单项详情(默认 0)。mode=index 将全部 job 的精简结果写入本地 JSONL 索引,只返回计数、complete、index_path 和更新时间;complete 仅表示执行均已终结,unavailable_outputs 表示尚不可用文件数。默认按需下载,不触发生成;可用 get_batch 轮询进度。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_id | string | yes | run_workflow 返回的 batch_id |
| mode | string | no | index:批次完整本地索引;省略:兼容单项查询 |
| index | integer | no | 运行序号(单运行为 0) |
| download | boolean | no | succeeded 且输出未落盘时按需下载(默认 true,幂等) |
查询批量运行全貌:batch 状态 + 逐状态统计(succeeded/failed/running/queued/pending/invalid/unknown/paused——submission_unknown 与 paused 单列,绝不混入 failed)+ 分页 job 列表(有界字段:状态/attempt/错误摘要/输出数,不含完整参数与日志)。status 可过滤:pending|invalid|submitting|unknown|queued|executing|succeeded|failed|timeout|cancelled|paused。
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_id | string | yes | run_workflow 返回的 batch_id |
| limit | integer | no | 分页大小,默认 20,上限 100 |
| offset | integer | no | 分页偏移,默认 0 |
| status | string | no | 可选:按 job 状态过滤列表(统计不受影响) |
- 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 Light 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 | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 (4 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_workflows | no tags | |
| run_workflow | no tags | |
| get_result | no tags | |
| get_batch | 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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
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 0.3.0-rc.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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 Light 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.