Back to MCP Trust Indexm8ven
F
Warning
28/100
1 day ago

void

A privacy-first AI desktop assistant with a glassmorphic floating UI, local LLM (Qwen3b), OCR, voice control, and deep system integration — built with PyQt6.

→ MKarthik730/void· 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 pushwhy connect →

Who stands behind it

MKarthik730

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

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

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: GOOGLE_OAUTH_CLIENT_ID. We can’t prove the destination matches the brand the credential belongs to.
🚨
Code appears obfuscated
2 files are unreadable to a human reviewer. Cannot audit what they do.
🔐
You'll be asked for 9 credentials: IMAP_PASSWORD, HF_TOKEN, HUGGING_FACE_HUB_TOKEN, VOID_ADMIN_PASSWORD, VOID_INTERNAL_TOKEN, CARDDAV_PASSWORD, GOOGLE_OAUTH_CLIENT_SECRET, EMBEDDING_API_KEY, OPENAI_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.
configALLOWED_ORIGINS
configREQUEST_HARD_TIMEOUT
configAUTH_ENABLEDDefaults work out of the box: clone, run, then configure models, search, and email inside Settings. Only edit .env for deployment-level overrides such as APP_BIND, APP_PORT, , or DATABASE_URL.
configLOCALHOST_BYPASSKeep AUTH_ENABLED=true for any network-accessible deployment and =false outside local development.
configOLLAMA_BASE_URL
configOLLAMA_URL
configVOID_MODEL_KEEPALIVE
configVOID_INPROCESS_TASKS
configAPP_BINDDefaults work out of the box: clone, run, then configure models, search, and email inside Settings. Only edit .env for deployment-level overrides such as , APP_PORT, AUTH_ENABLED, or DATABASE_URL.
configAPP_PORTDefaults work out of the box: clone, run, then configure models, search, and email inside Settings. Only edit .env for deployment-level overrides such as APP_BIND, , AUTH_ENABLED, or DATABASE_URL.
configOAUTH_REDIRECT_BASE_URL
configAPP_PUBLIC_URL
configEMAIL_SOCKET_TIMEOUT
configVOID_DOCUMENT_OWNER
configIMAP_HOST
configIMAP_PORT
configIMAP_USER
🔐 secretIMAP_PASSWORD
configIMAP_SSL
configIMAP_STARTTLS
configEMAIL_FROM
configARCHIVE_FOLDER
configTRASH_FOLDER
configVOID_DISABLE_MCP
configVOID_MCP_ALLOWED_COMMANDS
🔐 secretHF_TOKEN
🔐 secretHUGGING_FACE_HUB_TOKEN
configVOID_ADMIN_USER
🔐 secretVOID_ADMIN_PASSWORD
configVOID_SKIP_ADMIN_PROMPT
configVOID_SKIP_RUN_HINT
🔐 secretVOID_INTERNAL_TOKEN
configComSpec
configSECURE_COOKIES
configVOID_FALLBACK_OWNER
configVOID_SINGLE_USER
🔐 secretCARDDAV_PASSWORD
configCARDDAV_URL
configCARDDAV_USERNAME
configCARDDAV_BLOCK_PRIVATE_IPS
configDATA_DIR
configHUGGINGFACE_HUB_CACHE
configHF_HOME
configVOID_ALLOW_OLLAMA_CLI_SCAN
configGOOGLE_OAUTH_CLIENT_ID
🔐 secretGOOGLE_OAUTH_CLIENT_SECRET
configVOID_IMAP_TIMEOUT_SECONDS
configVOID_INPROCESS_POLLERS
configGOOGLE_OAUTH_REDIRECT_URI
configFASTEMBED_MODEL
configEMBEDDING_URL
configEMBEDDING_MODEL
configEMBEDDING_BLOCK_PRIVATE_IPS
🔐 secretEMBEDDING_API_KEY
configREMINDER_WEBHOOK_BLOCK_PRIVATE_IPS
configHF_HUB_DISABLE_PROGRESS_BARS
configHF_HUB_DOWNLOAD_MAX_WORKERS
configTERM
configCOLORTERM
configIMAGE_BLOCK_PRIVATE_IPS
configVOID_SCRIPT_HOST
configVOID_ALLOW_PRIVATE_CALDAV
configCHATGPT_SUBSCRIPTION_BASE_URL
configCHROMADB_CONNECT_TIMEOUT
configCHROMADB_HOST
configCHROMADB_PORT
configVOID_DATA_DIR
configVOID_MAIL_ATTACHMENTS_DIR
configFASTEMBED_CACHE_PATH
configLLM_HOST
configLLM_HOSTS
🔐 secretOPENAI_API_KEY
configSEARXNG_INSTANCE
configCLEANUP_ENABLED
configCLEANUP_INTERVAL_HOURS
configVOID_INTERNAL_BASE
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deploySMTP_HOST
deploySMTP_PORT
deploySMTP_SECURITY
deploySMTP_USER
deploySMTP_PASSWORD
deploySMTP_STARTTLS
deploySMTP_SSL
deployDATABASE_URL
// 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

21/21 tools missing one or more hints — call_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_email_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_emails (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +18 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.

Readable source code

2 files appear obfuscated

Ship unminified, readable source.

Secrets not logged

7 secret values sent to console.log

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/mkarthik730-void-9ydu3h?variant=verified)](https://m8ven.ai/mcp/mkarthik730-void-9ydu3h)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 633584aeae3f7f7f2e9d6457f8bb0e541ee167f6
code hash: 86c80d67b2043dbd22c83941f8c499882b16bf6f4144741d8006a055500fe817
verified: 8/18/2026, 9:21:55 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