Comfy Cozy (JosephOIbrahim/Comfy-Cozy) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 3 tools. No publisher has claimed this listing.

Emerging

74/100

24 days ago

Comfy Cozy

Item: Comfy Cozy
Rating: 74
Author: M8ven

A plain-English co-pilot for ComfyUI that lets you describe image generation changes in natural language, automatically loading workflows, swapping models, tweaking parameters, and running generations while learning your preferences.

→ JosephOIbrahim/Comfy-Cozy · listed on glama

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

JosephOIbrahim

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Known vulnerabilities in dependencies: 1 critical

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 10 credentials: ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, NVIDIA_API_KEY, OPENROUTER_API_KEY, CUSTOM_API_KEY, MCP_AUTH_TOKEN, GITHUB_API_TOKEN, HF_TOKEN, GOOGLE_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// known CVEs in dependencies1 critical

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@1.6.1GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configCOMFY_COZY_MCP

configNIM_HOST_ID

configCOMFYUI_HOST127.0.0.1 Where ComfyUI runs

configCOMFYUI_PORT8188 ComfyUI port

configCOMFYUI_PATH

configLLM_PROVIDERRun (=custom is already set above)

🔐 secretANTHROPIC_API_KEYsk-ant-your-key-here

🔐 secretOPENAI_API_KEYsk-your-key-here

🔐 secretGEMINI_API_KEYyour-key-here

configOLLAMA_BASE_URLUses Ollama's OpenAI-compatible endpoint at localhost:11434. Override with if running remotely. No data leaves your machine.

configNVIDIA_BASE_URL

🔐 secretNVIDIA_API_KEYnvapi-your-key-here

configNVIDIA_EMIT_REASONING

🔐 secretOPENROUTER_API_KEY

configCUSTOM_BASE_URL

🔐 secretCUSTOM_API_KEYoptional -- many local servers need none

configCUSTOM_MODELmy-local-model # the model id your endpoint serves

configVISION_PROVIDER

🔐 secretMCP_AUTH_TOKEN

🔐 secretGITHUB_API_TOKEN

🔐 secretHF_TOKEN

configVISION_MODEL=claude-opus-4-7 -- analyze/compare images

configTHINKING_BUDGET=4000 -- agent reasoning budget (tokens)

configVISION_THINKING_BUDGET=2000 -- vision reasoning budget

configTHINKING_EFFORT

configCOMPACT_THRESHOLD

configNVIDIA_CONTEXT_WINDOW

configCOMFYUI_ENDPOINTS

configBRAIN_ENABLEDDAG_ENABLED GATE_ENABLED OBSERVATION_ENABLED

configOBSERVATION_ENABLEDBRAIN_ENABLED DAG_ENABLED GATE_ENABLED

configDAG_ENABLEDBRAIN_ENABLED GATE_ENABLED OBSERVATION_ENABLED

configGATE_ENABLEDBRAIN_ENABLED DAG_ENABLED OBSERVATION_ENABLED

configRECIPES_ENABLED

configCOMFYUI_DATABASEC:/path/to/your/ComfyUI

configCOMFYUI_OUTPUT_DIR

configCOMFYUI_INSTALL_DIR

configAUTO_SCAN_MODELS

configAUTO_SCAN_WORKFLOWS

configAUTO_LOAD_WORKFLOW

configAUTO_LOAD_SESSION

configSTAGE_DEFAULT_PATH

configSTAGE_AUTOSAVE_SECONDS

configSTAGE_AUTOLOAD_EXPERIENCE

configCOMFY_COZY_HOME~/.comfy-cozy Where an installed package keeps its state (.env, sessions, logs); checkouts keep repo-root sessions/ and logs/

configLOG_FORMAT

configDIAGNOSIS_DIR

configAI_ENGINETool["agent/tools/comfy_execute.py<br/>queue / poll / ws / status"] --> Get["get_engine()<br/>thread-safe cache<br/>env var "]

configMONETA_OUTBOX_DIR

configMONETA_INBOX_DIR

configMONETA_POLL_SECONDS

🔐 secretGOOGLE_API_KEY

configMODEL_SELECTION_PATH~/.comfy-cozy/model_selection.json Where your last model pick is remembered across restarts

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

3/3 tools missing one or more hints — call_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); comfyui_agent_ping (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); dynamic_tool_256 (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

2/3 tools referenced in tests (67%)

Write tests that reference each tool by name so every tool has at least one test.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/josephoibrahim/comfy-cozy)](https://m8ven.ai/mcp/josephoibrahim/comfy-cozy)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: 7c041174485e0d14749101daf0be2c2afaa83024

code hash: 298239c07a2ab1a2c4c331c23bb7dcb1e69ee6e46c849c6dee11d7cdc14f879c

verified: 8/17/2026, 3:47:51 PM

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client