D
Warning
56/100
8 hours ago

Bench Studio MCP Server

A local-first creative studio MCP server that provides access to 73 curated image and video generation models across 5 providers, enabling users to generate, refine, and manage creative outputs with transparent cost tracking and local file custody.

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

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

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

inematds

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 →

Install from

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

// key findings
🚨
Secret credentials may flow to a network call
8 flows detected: FAL_KEY, GOOGLE_API_KEY, OPENROUTER_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
⚠️
Tool descriptions don’t match what handlers do
5 tools describe read intent but their handlers mutate — list_models (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {); create_media (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {); sync_models (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {)
🔐
You'll be asked for 6 credentials: AGNES_API_KEY, BENCH_PASSWORD, FAL_KEY, GOOGLE_API_KEY, KIE_API_KEY, OPENROUTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// 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.
🔐 secretAGNES_API_KEY[Agnes AI](https://apihub.agnes-ai.com) 4 zero
configBENCH_API_HOSTloopback (), so the endpoint that writes files and spends money
configBENCH_API_PORTPORT=8790 =8790 BENCH_WEB_PORT=5201 npm run dev
configBENCH_CHROME
configBENCH_DATA_DIR
configBENCH_DOCUMENT_REFERENCE
🔐 secretBENCH_PASSWORDOptional password. Set and the API requires a session:
configBENCH_REUSE_SERVER
configBENCH_URL
configBENCH_WEBSITE_REFERENCE
configBENCH_WEBSITE_REFERENCE_URL
configBENCH_WEB_HOST
configBENCH_WEB_PORTPORT=8790 BENCH_API_PORT=8790 =5201 npm run dev
🔐 secretFAL_KEY[fal.ai](https://fal.ai/dashboard/keys) 37 dollars, live pricing
configFFMPEG_PATH
🔐 secretGOOGLE_API_KEY
configINEMAIMG_URL
🔐 secretKIE_API_KEY[kie.ai](https://kie.ai/api-key) 4 credits
configOLLAMA_URL
🔐 secretOPENROUTER_API_KEY
configOPENROUTER_BASE_URL
configOPENROUTER_MODEL_DEFAULT
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Dependencies

14 dependencies, 2 flagged: @axe-core/playwright, @playwright/test

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

10/10 tools missing one or more hints — list_models (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_model_capabilities (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); upload_media (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 more. 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.

Descriptions match behaviour

5 tools describe read intent but their handlers mutate — list_models (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {); create_media (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {); sync_models (line 38: spawn(process.execPath, [join(HERE, "server.mjs")], {)

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool test coverage

Only 0/10 tools referenced in tests (0%)

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

Shell command execution

10 child_process/subprocess calls in production code — runs shell commands (server/server.mjs:356, server/server.mjs:1539, server/server.mjs:1740)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets stay with their owner

4 secret/sensitive values flow into network calls (FAL_KEY → dynamic, FAL_KEY → dynamic) (4 other flows matched canonical API hosts)

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

Secrets not logged

9 secret values sent to console.log

Redact or omit secret values from log output.

Tool description accuracy

5 tools have description/behavior mismatches: list_models: description implies read-only but handler writes/deletes/executes; create_media: description implies read-only but handler writes/deletes/executes; sync_models: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

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 8 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 Verified](https://m8ven.ai/badge/mcp/inematds-bench-studio-en-13si8r?variant=verified)](https://m8ven.ai/mcp/inematds-bench-studio-en-13si8r)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: b880df5ab1a60a2ca9a8a0da33d66409aeb091fb
code hash: 8410024cf1be3b69284c2cf34783d309d255f7b8cbb8367b216fd5e9d72952c2
verified: 8/19/2026, 9:10:02 AM
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