mcp@1.26.0

VERIFIED· startup only

Publisher claims: "Reference implementation of the KYA-OS protocol for Model Context Protocol servers: identity, delegation, proofs, sessions, and verifiable audit trails" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher kya-os · publishing for 191 daysInstalls 74,037Last detonated 15 min ago
$claude mcp add mcp -- npx -y @kya-os/mcp
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MAX_CREDENTIAL_NESTING_DEPTHConfiguration, not credentials: KYA_OS_CARD_META_KEY, KYA_OS_CARD_WELL_KNOWN_PATH, KYA_OS_DID_META_KEY
Where it talks to
kya-os.org (its own)
What we saw when it ran
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for MAX_CREDENTIAL_NESTING_DEPTH and talks to kya-os.org. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets MAX_CREDENTIAL_NESTING_DEPTH=kya-os.org -- npx -y @kya-os/mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.25.0

vet-skills diff mcp 1.25.0 1.26.0

This version reaches for something 1.25.0 did not: 1 new credential variable (MAX_CREDENTIAL_NESTING_DEPTH). Compared from the two recorded runs, not from source.

New credential variables
MAX_CREDENTIAL_NESTING_DEPTH

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 35 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
15sprocessdependency install exit 0
35sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-Vn4oBJ/task/home/work/acme-api/.claude/skills/mcp/dist/audit/replay-bundle.js' } Node.js v22.23.5
35sprocessscript backend runs setup only
35sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commanddist/card/build.d.ts:25 · Process kill command — agent can terminate processes/** W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/emit.js:108 · Process kill command — agent can terminate processes* (`delegationRef` proves the `responsibleParty` claim; `revocation` is the kill switch). CarryingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/builder.d.ts:86 · Process kill command — agent can terminate processes/** Attach the W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagepackage.json:110 · npx invocation of non-well-known package — may execute untrusted code"changie": "npx --yes [email protected]",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/card/emit.d.ts:50 · Process kill command — agent can terminate processes* `revocation` (the post-issuance kill switch) — so the projection stays self-verifiable and canFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/resolve.js:122 · Process kill command — agent can terminate processes* fail-closed because the summary now carries the `revocation` kill switch and `delegationRef`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/resolve.d.ts:17 · Process kill command — agent can terminate processes* directly — fail-closed because the summary carries the `revocation` kill switch andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/builder.js:106 · Process kill command — agent can terminate processes/** Attach the W3C Bitstring Status List revocation entry (the post-issuance kill switch). */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/card/resolve.js:17 · Process kill command — agent can terminate processes* directly — fail-closed because the summary carries the `revocation` kill switch andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈72 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.