Harnios MCP (harnios/harnios-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 21 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
56/100

Harnios MCP

Harnios is a self-hosted, MCP-based storage system that gives every AI assistant you use — Claude, ChatGPT, Cursor, or anything else — a shared, persistent memory of your business: knowledge base, skills, projects, operational tables, and reports, all in one place. Connect a new tool once, and it reads and writes through the same store instead of starting from zero.

→ harnios/harnios-mcp· listed on glama

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

harnios

Source: Glama · also listed on 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

Glamanot scored hereGitHub

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: 2 critical, 5 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 4 credentials: MISTRAL_API_KEY, OAUTH_OWNER_PASSWORD, S3_SECRET_ACCESS_KEY, TELEGRAM_BOT_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes21 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.

create_file
read_file
delete_file
create_directory
list_directory
delete_directory
update_file
move
get_docs
get_os_engine
get_os_upgrade
get_os_init
get_change_process
get_inbox
run_job

Runs a registered workflow stored under os/jobs in the workspace. Supply its jobId and declared arguments only. The job can access only its manifest-authorized files and returns output metadata plus an aggregate summary, never file contents.

send_email
send_telegram_message
run_python
list_directory_tree
find_files_by_name
search_file_content
// known CVEs in dependencies2 critical5 high5 medium3 low

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

criticalnext@16.2.10GHSA-2xp9-vwfh-vxw4

Next.js: Unauthenticated Remote Code Execution in Image Optimization API when AVIF files are used

criticalnext@16.2.10GHSA-p293-qw3h-jr36

Next.js: Unauthenticated Remote Code Execution on windows-hosted servers

highnext@16.2.10GHSA-6gpp-xcg3-4w24

Next.js: Middleware / Proxy bypass in App Router applications using Turbopack and single locale

highnext@16.2.10GHSA-89xv-2m56-2m9x

Next.js: Server-Side Request Forgery in Server Actions on custom servers

highnext@16.2.10GHSA-m99w-x7hq-7vfj

Next.js: Denial of Service in App Router using Server Actions

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.
configMCP_BOOTSTRAP_PATH
configMESSAGING_RATE_LIMIT_MAX
configMESSAGING_RATE_LIMIT_WINDOW_MINUTES
🔐 secretMISTRAL_API_KEY
configMISTRAL_MODEL
🔐 secretOAUTH_OWNER_PASSWORD
configOAUTH_OWNER_USERNAME
configOS_NAME
configS3_ACCESS_KEY_ID
configS3_BUCKET
configS3_ENDPOINT
configS3_FORCE_PATH_STYLE
configS3_REGION
🔐 secretS3_SECRET_ACCESS_KEY
configSCHEDULER_ENABLED
configSCHEDULER_TIMEZONE
🔐 secretTELEGRAM_BOT_TOKEN
configTELEGRAM_CHAT_ID
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deploySMTP_FROM
deploySMTP_HOST
deploySMTP_PASSWORD
deploySMTP_PORT
deploySMTP_SECURE
deploySMTP_USER
// 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 — create_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); delete_file (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.

Tool test coverage

Only 2/21 tools referenced in tests (10%)

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

Production dependencies are patched

2 critical, 5 high severity in production deps — next@16.2.10 (critical), next@16.2.10 (critical)

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

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/harnios/harnios-mcp?variant=verified)](https://m8ven.ai/mcp/harnios/harnios-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 7f1cdf79d80d08a9d06af0eb2b3319e048a555bc
code hash: 22973b0608feeb951df4b1671d46ff6cf28d0b1f2c2655e5e74ef7c69d8dea39
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