Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MetaBrain-Labs/ComfyUI-MCP-Server-TypeScript --skill comfyui-mcp-server-skillgit clone --depth 1 https://github.com/MetaBrain-Labs/ComfyUI-MCP-Server-TypeScriptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/metabrain-labs/comfyui-mcp-server-typescript/comfyui-mcp-server-skill)<a href="https://agentmods.dev/skills/metabrain-labs/comfyui-mcp-server-typescript/comfyui-mcp-server-skill"><img src="https://agentmods.dev/badge/skills/metabrain-labs/comfyui-mcp-server-typescript/comfyui-mcp-server-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/metabrain-labs/comfyui-mcp-server-typescript/comfyui-mcp-server-skill"><img src="https://agentmods.dev/badge/skills/metabrain-labs/comfyui-mcp-server-typescript/comfyui-mcp-server-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00373 |
| Opus 5.5 | $0.00024 | $0.00149 |
| Sonnet 5.5 | $0.00012 | $0.00075 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
comfyui-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Use Cases
Activate this skill when users request generate image, video, or multimedia generation. Your role is the ComfyUI Intelligent Operator—coordinating generative AI tasks via the ComfyUI MCP Server through a strict sequential tool protocol.
Usage Method
Mandatory Initialization
Before executing any workflow task:
- Read
rules/**.md - Follow the tool calling sequence described there.
- Do not skip this step.
Refer to the respective rule files for detailed instructions and code examples:
If the user does not specify, this rule is applied.
- rules/catalog.md - Generate images and videos by constructing workflow directories
- references/catalog.md - Reference examples for generating images and videos via the build workflow directory
- rules/api-json.md - Generate images and videos using user-provided API JSON
- references/Catalog.md - Reference examples for generating images and videos using user-provided API JSON
Important Notes
-
When using this tool within MCP service workflow types, if asynchronous execution is not specified, it is strictly prohibited to invoke other MCP tools during tool operation to check intermediate results or perform actions. Wait for the tool to complete execution.
-
Long-running tasks within workflow types have a maximum timeout configuration; there is no need to manually disconnect.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 44 lines · 61 tokens per session scan A 253dcb9b032c
comfyui-mcp-server is a skill published in the GitHub repository MetaBrain-Labs/ComfyUI-MCP-Server-TypeScript (10 stars, last pushed 7mo ago), licensed MIT. It adds 61 tokens to every session and 373 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
comfyui-mcp-server compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| comfyui-mcp-serverMetaBrain-Labs/ComfyUI-MCP-Server-TypeScript | Skill | 10 | 7mo ago | MIT | A | 61 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | today | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 480 | today | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |