tankpkg/tank (tankpkg/tank) is an MCP server listed on the M8ven Trust Index. It scores 43 out of 100, grade D. It declares 17 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
43/100

tankpkg/tank

MCP server for Tank - scan and publish AI agent skills from your editor

→ tankpkg/tank· npm: @tankpkg/mcp-server· listed on npm

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

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

tankpkg

Source: npm

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

npmscored separately

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: 1 critical, 2 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 1 credential: TANK_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes17 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.

audit-skill

Show security audit results for a skill from the Tank registry.

doctor

Diagnose Tank setup and environment.

init-skill
install-skill
link-skill

Link an installed skill into an agent workspace. Creates a symlink from the workspace .skills directory to the installed skill.

login

Authenticate with Tank using GitHub OAuth device flow. Opens browser for authorization.

logout

Log out of Tank by clearing local credentials.

publish-skill

Publish a skill to the Tank registry. Requires authentication.

remove-skill
scan-skill

Scan a skill directory for security issues. Requires authentication.

search-skills

Search the Tank registry for AI agent skills

skill-info

Get detailed information about a specific skill from the Tank registry

skill-permissions

Display resolved permission summary for installed skills. Shows what capabilities each skill requires and checks against the project permission budget.

unlink-skill

Unlink a skill from an agent workspace. Removes the symlink without deleting the installed skill files.

update-skill

Update an installed skill to the latest compatible version within its declared semver range.

verify-skills

Verify that installed skills match their lockfile entries. Checks that skill directories exist and are not empty.

whoami

Show the authenticated Tank user for the current local session.

// known CVEs in dependencies1 critical2 high1 medium3 low

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

criticaltar@7.5.11GHSA-23hp-3jrh-7fpw

node-tar: Decompression/parse DoS via unlimited input

hightar@7.5.11GHSA-8x88-c5mf-7j5w

node-tar: Negative tar entry size causes infinite loop in archive replace

hightar@7.5.11GHSA-r292-9mhp-454m

node-tar: Uncontrolled recursion in mapHas/filesFilter allows uncatchable stack-overflow DoS via crafted long-path tar with member selection

mediumtar@7.5.11GHSA-vmf3-w455-68vh

node-tar applies PAX size override to intermediary GNU long-name/long-link headers, causing tar parser interpretation differential (file smuggling)

lowtar@7.5.11GHSA-gvwx-54wh-qm9j

node-tar: Uncaught Exception DoS via NUL byte in PAX path/linkpath records

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.
🔐 secretTANK_TOKENAlternatively, set the environment variable:
// 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

17/17 tools missing one or more hints — audit-skill (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); doctor (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); init-skill (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 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.

Destructive tools are labelled

5 tools perform destructive updates without destructiveHint — install-skill deletes at line 295 (fs.unlinkSync(tmpTarball)); link-skill deletes at line 85 (fs.unlinkSync(symlinkPath)); remove-skill deletes at line 103 (fs.rmSync(skillDir, { recursive: true, force: true }))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool test coverage

Only 0/17 tools referenced in tests (0%)

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

Production dependencies are patched

1 critical, 2 high severity in production deps — tar@7.5.11 (critical), tar@7.5.11 (high)

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 5 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/tankpkg/tank~packages~mcp-server?variant=verified)](https://m8ven.ai/mcp/tankpkg/tank~packages~mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 51b0ce1a650cfcf09411307b41c74eafe7d62925
code hash: 8ba963c1d127e589ae82c5a5109dd6d23a720bf1c0f0e08133f8fb9cd2168c2b
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