tao-skill-bank (NVIDIA-TAO/tao-skill-bank) is an MCP server listed on the M8ven Trust Index. It scores 45 out of 100, grade D. It declares 12 tools. No publisher has claimed this listing.

Warning

45/100

tao-skill-bank

Item: tao-skill-bank
Rating: 45
Author: M8ven

→ NVIDIA-TAO/tao-skill-bank · listed on github_code

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

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

NVIDIA-TAO

Source: github_code

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

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Reads files from sensitive locations

Touches: ~/.tao/config.env

🔐

You'll be asked for 6 credentials: TAO_MCP_TOKEN, AUTOML_LLM_API_KEY, ACCESS_KEY, SECRET_KEY, BREV_API_TOKEN, HF_TOKEN

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.

configTAO_SHELL_IMAGE

🔐 secretTAO_MCP_TOKEN

configTAO_SKILL_BANK_PATH

configAOI_WORKSPACE

configLUSTRE_TRAIN_CSV

configLUSTRE_VAL_CSV

configLUSTRE_IMAGES_DIR

configSLURM_BASE_RESULTS_DIR

configSLURM_PARTITION

configSLURM_ACCOUNT

configSLURM_USER

configSLURM_HOSTNAME

configLUSTRE_AOI_ROOT

configLUSTRE_KPI_CSV

configbase_url

configmodelWhen a workflow needs Hugging Face access, get a token from [Hugging Face settings](https://huggingface.co/settings/tokens) and accept the or dataset license before launch.

🔐 secretAUTOML_LLM_API_KEY

configSSH_KEY_PATH

configTAO_GPU_SMOKE_IMAGE

🔐 secretACCESS_KEYS3 / object-storage I/O via tao-data-io (legacy ACCESS_KEY/SECRET_KEY still accepted)

🔐 secretSECRET_KEYS3 / object-storage I/O via tao-data-io (legacy ACCESS_KEY/SECRET_KEY still accepted)

configCLOUD_REGION

configS3_ENDPOINT_URL

configCUDA_VISIBLE_DEVICES

🔐 secretBREV_API_TOKENtao-run-on-brev (optional — brev login also works)

configKUBECONFIG

configTAO_K8S_CONTEXT

configTAO_K8S_NAMESPACE

configDOCKER_HOSTtao-run-on-docker (local daemon or DOCKER_HOST=ssh://), tao-run-on-brev (instance-based GPU), tao-run-on-slurm (remote SLURM cluster), tao-run-on-kubernetes (k8s), tao-run-on-virtualenv (docker-free local venv), tao-data-io (S3/data staging), tao-setup-nvidia-gpu-host (host runtime)

configTAO_STATE_DIR

configAIR_GAPPED

configHF_HUB_OFFLINE

🔐 secretHF_TOKENgated HuggingFace models / push_to_hub

configLOGNAME

configVIRTUAL_ENV

configHF_MODEL_ID

configHF_MODEL_REVISION

configTAO_VIDEO_DECODER_DEVICE

configTAO_VIDEO_CACHE_SIZE

configTAO_FRAMEWORK_SFT_PROCESS_THREADS

configTAO_FRAMEWORK_DATALOADER_NUM_WORKERS

configTAO_VIDEO_DECODER_THREADS

configTAO_FRAMEWORK_VALIDATION_BATCH_SIZE

configTAO_FRAMEWORK_VALIDATION_SHARD_STRATEGY

configTAO_FRAMEWORK_VALIDATION_VIDEO_FEATURE_CACHE_SIZE

configTAO_FRAMEWORK_VALIDATION_PROCESSED_VIDEO_CACHE_SIZE

configTAO_FRAMEWORK_VALIDATION_CACHE_FRONTLOAD_UNIQUE_PER_BATCH

configCOSMOS_SFT_REQUIRE_VISUAL_GRADIENTS

configTAO_COSMOS_RL_DERIVATIVE

configTAO_VALIDATION_VIDEO_FEATURE_CACHE_SIZE

configFORCE_QWENVL_VIDEO_READER

configTAO_PYNV_FRAME_TRANSFER

configBASE_MODEL

configBASE_MODEL_REVISION

configARCHITECTURE_MODEL

configARCHITECTURE_MODEL_REVISION

configAWS_ENDPOINT_URLS3 / object-storage I/O via tao-data-io (legacy ACCESS_KEY/SECRET_KEY still accepted)

configAWS_DEFAULT_REGIONS3 / object-storage I/O via tao-data-io (legacy ACCESS_KEY/SECRET_KEY still accepted)

configTAO_RUNNER_GATE_TIMEOUT

// 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

12/12 tools missing one or more hints — tao_ls (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); tao_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); tao_write (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +9 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.

No access to sensitive paths

Reads sensitive paths: ~/.tao/config.env

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Secrets not logged

3 secret values sent to log.info/print

Redact or omit secret values from log output.

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 Verified](https://m8ven.ai/badge/mcp/nvidia-tao/tao-skill-bank?variant=verified)](https://m8ven.ai/mcp/nvidia-tao/tao-skill-bank)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 025107e6257195b2b97535efafb3c04aa2fdfed7

code hash: 866e803cda1cc2dfe42516940c52012110347cb9d302fa76c62b1a77704618f8

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