NeoAgent (NeoLabs-Systems/NeoAgent) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 5 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
54/100

NeoAgent

Self-hosted AI agent for automation, messaging, tools, integrations, and device control.

→ NeoLabs-Systems/NeoAgent· listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. 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

NeoLabs-Systems

Source: github_repo_search

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
⚠️
Known vulnerabilities in dependencies: 5 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 19 credentials: ADMIN_API_KEY, ADMIN_PASSWORD, BRAVE_SEARCH_API_KEY, DEEPGRAM_API_KEY, FIGMA_OAUTH_CLIENT_SECRET, GOOGLE_OAUTH_CLIENT_SECRET, MICROSOFT_OAUTH_CLIENT_SECRET, NEOAGENT_DATA_ENCRYPTION_KEY, NEOAGENT_RUNTIME_PUBLIC_KEY, NEOAGENT_VM_GUEST_TOKEN, NOTION_OAUTH_CLIENT_SECRET, OPENAI_API_KEY, OPENAI_COMPATIBLE_API_KEY, SESSION_SECRET, SLACK_OAUTH_CLIENT_SECRET, STRIPE_PUBLISHABLE_KEY, STRIPE_SECRET_KEY, STRIPE_WEBHOOK_SECRET, XAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes5 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

detect_synthid_watermark

Check a PNG or JPEG image for Google's invisible SynthID watermark using the official Vertex AI detector. A negative result does not prove that an image is human-made or not AI-generated.

task_complete

Signal that the task is terminal and provide the final response. Valid terminal states include: completed successfully, already done/no matching change needed, or impossible/blocked with concrete evidence. Call this exactly once when you have the final user-ready answer. Do NOT call it if you still …

send_interim_update

Send a short user-visible interim update only when there is materially useful new progress, a real blocker, or a blocking question. Never use this for internal monologue, self-checks, tool bookkeeping, or "nothing happened" status.

request_user_input

Pause this Cowork run and ask one to three structured questions only when an irreversible product choice is missing. Give two or three options per question, mark the recommended option, and permit a custom answer. Do not use this to ask for a project URL, repo, or permission to edit files that are a…

neoagent_turn

Send the caller transcript to the canonical NeoAgent chat runtime. Required for every substantive turn and every active-run control request.

// known CVEs in dependencies5 high5 low

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

highmulter@2.2.0GHSA-535w-7cp7-47q4

multer vulnerable to Denial of Service via oversized array index in field names

highmulter@2.2.0GHSA-qfvm-cv95-jqjf

multer vulnerable to Denial of Service via file descriptor leak on aborted uploads

highmulter@2.2.0GHSA-wc9g-mqfw-jrwm

multer vulnerable to Denial of Service via crafted multipart field names

highnodemailer@9.0.5GHSA-2x7j-588g-ccc2

Nodemailer: Quadratic (O(n²)) time complexity in addressparser allows remote denial of service via a crafted address list

highsharp@0.35.3GHSA-rgj7-g3m4-5g8c

sharp: Vulnerabilities in libheif: GHSA-g89c-p67h-r497 and GHSA-2jg2-4ch7-h545

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.
🔐 secretADMIN_API_KEY
🔐 secretADMIN_PASSWORD
configADMIN_USERNAME
configALLOWED_ORIGINS
🔐 secretBRAVE_SEARCH_API_KEY
🔐 secretDEEPGRAM_API_KEY
configDEEPGRAM_BASE_URL
configDEEPGRAM_LANGUAGE
configDEEPGRAM_MODEL
configDISPLAY
configFIGMA_OAUTH_CLIENT_ID
🔐 secretFIGMA_OAUTH_CLIENT_SECRET
configGIT_SHA
configGOOGLE_OAUTH_CLIENT_ID
🔐 secretGOOGLE_OAUTH_CLIENT_SECRET
configMICROSOFT_OAUTH_CLIENT_ID
🔐 secretMICROSOFT_OAUTH_CLIENT_SECRET
configNEOAGENT_AGENT_DATA_DIR
configNEOAGENT_ALLOW_SIGNUP
configNEOAGENT_BACKEND_URL
configNEOAGENT_DATA_DIR
🔐 secretNEOAGENT_DATA_ENCRYPTION_KEY
configNEOAGENT_ENV_FILE
configNEOAGENT_GUEST_AGENT_PORT
configNEOAGENT_GUEST_MAX_APK_STREAM_BYTES
configNEOAGENT_GUEST_MAX_WORKSPACE_IMPORT_BYTES
configNEOAGENT_GUEST_MIN_FREE_DISK_BYTES
configNEOAGENT_GUEST_PROFILE
configNEOAGENT_HOME
configNEOAGENT_HSTS_MAX_AGE
configNEOAGENT_HTTP_ALLOW_PRIVATE
configNEOAGENT_MEMORY_INGESTION_INTERVAL_MS
configNEOAGENT_PROFILE
configNEOAGENT_RATE_LIMIT_4H
configNEOAGENT_RATE_LIMIT_WEEKLY
configNEOAGENT_RELEASE_CHANNEL
🔐 secretNEOAGENT_RUNTIME_PUBLIC_KEY
configNEOAGENT_SOCKET_CONNECT_TIMEOUT_MS
configNEOAGENT_SOCKET_MAX_HTTP_BUFFER_BYTES
configNEOAGENT_SOCKET_PING_INTERVAL_MS
configNEOAGENT_SOCKET_PING_TIMEOUT_MS
configNEOAGENT_VM_BASE_IMAGE
configNEOAGENT_VM_BASE_IMAGE_URL
🔐 secretNEOAGENT_VM_GUEST_TOKEN
configNEOAGENT_VM_GUEST_TOKEN_B64
configNEOAGENT_WORKSPACE_DIR
configNOTION_OAUTH_CLIENT_ID
🔐 secretNOTION_OAUTH_CLIENT_SECRET
🔐 secretOPENAI_API_KEY
🔐 secretOPENAI_COMPATIBLE_API_KEY
configOPENAI_COMPATIBLE_BASE_URL
configPLAYWRIGHT_SKIP_BROWSER_DOWNLOAD
configPUBLIC_URL
configPUPPETEER_SKIP_DOWNLOAD
configProgramFiles
configSECURE_COOKIES
🔐 secretSESSION_SECRET
configSLACK_OAUTH_CLIENT_ID
🔐 secretSLACK_OAUTH_CLIENT_SECRET
🔐 secretSTRIPE_PUBLISHABLE_KEY
🔐 secretSTRIPE_SECRET_KEY
🔐 secretSTRIPE_WEBHOOK_SECRET
configTRUST_PROXY
🔐 secretXAI_API_KEY
configXAI_BASE_URL
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Dependencies

42 runtime dependencies (10 dev), 1 flagged: playwright-chromium

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

5/5 tools missing one or more hints — detect_synthid_watermark (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); task_complete (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); send_interim_update (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +2 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.

Shell command execution

1 call in production code run through a shell (server/utils/version.js:30)

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

Production dependencies are patched

0 critical, 5 high severity in production deps — multer@2.2.0 (high), multer@2.2.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

3/42 production deps abandoned (no release in 2+ years): better-sqlite3-session-store@2022-06-25 (4.2y), proper-lockfile@2022-06-24 (4.2y), @slidev/theme-default@2024-02-11 (2.6y)

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/neolabs-systems/neoagent?variant=verified)](https://m8ven.ai/mcp/neolabs-systems/neoagent)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: f6138ca1341d90930ffb6c5c9c44dcb4736ff44f
code hash: b18420df8294a7b47c4447d8428ea57be9f2cc423820c8634f89bca34b59acb1
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