Skills/npm/agenthub-multiagent-mcp

agenthub-multiagent-mcp@1.78.1

VERIFIED· not started

Publisher claims: "MCP server for AgentHub multi-agent communication" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher contetial · publishing for 327 daysInstalls 4,195Last detonated 20 h ago
$claude mcp add agenthub-multiagent-mcp -- npx -y agenthub-multiagent-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
AGENTHUB_API_KEYAGENTHUB_FASTPATH_API_KEYAGENTHUB_USER_API_KEYConfiguration, not credentials: AGENTHUB_AGENT_ID, AGENTHUB_ATTACHMENT_DIR, AGENTHUB_AUTO_ACTIVITY, AGENTHUB_AUTO_INBOX, AGENTHUB_AUTO_RECONNECT, AGENTHUB_BRAIN_BACKEND, AGENTHUB_BRAIN_MIGRATE_ATTEMPTS, AGENTHUB_DISABLE_WEBSOCKET, AGENTHUB_EMPLOYEE_RUNTIME_ENTRY, AGENTHUB_FASTPATH_BASE_URL, AGENTHUB_FASTPATH_ENABLED, AGENTHUB_FASTPATH_EXPERT_GROUNDING, AGENTHUB_FASTPATH_GROUNDING_K, AGENTHUB_FASTPATH_MODEL, AGENTHUB_FASTPATH_TIMEOUT_MS, AGENTHUB_HEADLESS, AGENTHUB_INTEGRATION_TESTS, AGENTHUB_MODEL, AGENTHUB_PROJECT, AGENTHUB_REQUEST_TIMEOUT_MS, AGENTHUB_SKILLS_AUTOINSTALL, AGENTHUB_URL
Where it talks to
no vendor host named in the codeAlso contetial.com, hub.test, proxy.local, agenthub.test, apple.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names contetial.com, hub.test, proxy.local, agenthub.test, apple.com as well as its own vendor. The guard injects AGENTHUB_API_KEY, AGENTHUB_FASTPATH_API_KEY, AGENTHUB_USER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y agenthub-multiagent-mcp

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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 89/100 (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 · 8 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.7sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-DFLTNk/task/home/.npm/_logs/2026-11-13T16_39_23_057Z-debug-0.log
7.7sclaimednot started: dependency install failed (exit 1); the server itself was not observed
7.7sprocessscript backend runs setup only
7.7sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commanddist/daemon.js:580 · Process kill command — agent can terminate processes// Timeout: kill if running too longFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/daemon.js:117 · Process kill command — agent can terminate processes// Force kill if still aliveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/channelSetup.js:94 · npx invocation of non-well-known package — may execute untrusted code// `npx agenthub-channel` resolves to a different package entirely.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/goshtiChannel.js:15 · npx invocation of non-well-known package — may execute untrusted code* claude mcp add --scope user goshti-channel -- npx -y -p agenthub-multiagent-mcp@latest goshti-channelFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/npxRetired.js:3 · npx invocation of non-well-known package — may execute untrusted code* package so the next `npx …@latest` upgrade can run.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/planHookCli.js:9 · npx invocation of non-well-known package — may execute untrusted code* echo '{"tool_name":"ExitPlanMode","tool_input":{"plan":"..."}}' | npx agenthub-hook plan-reviewFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/version.js:7 · npx invocation of non-well-known package — may execute untrusted code// launched from `npx -y agenthub-multiagent-mcp@latest` (unpacked in a cache)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/planHookCli.d.ts:9 · npx invocation of non-well-known package — may execute untrusted code* echo '{"tool_name":"ExitPlanMode","tool_input":{"plan":"..."}}' | npx agenthub-hook plan-reviewFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/tools/index.js:858 · Process kill command — agent can terminate processes…d path — the target must be on the deployment's file-delivery allowlist and the kill switch enabled, else the call is rejected (target_not_allowed / file_delivery_di…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/pinSweepCli.js:242 · npx invocation of non-well-known package — may execute untrusted codeprint(" Floating this pin has caused EBUSY on a shared npx cache while");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/pinSweep.d.ts:73 · npx invocation of non-well-known package — may execute untrusted code* floating that pin has caused `EBUSY` on a shared npx cache while anotherFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/index.js:311 · npx invocation of non-well-known package — may execute untrusted code// `npx …@latest` upgrade does not die with EBUSY on WindowsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/pinSweep.js:86 · npx invocation of non-well-known package — may execute untrusted code* floating that pin has caused `EBUSY` on a shared npx cache while anotherFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/steering.test.js:23 · Process kill command — agent can terminate processesdescribe("§4.8 kill switch", () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/npxRetired.d.ts:3 · npx invocation of non-well-known package — may execute untrusted code* package so the next `npx …@latest` upgrade can run.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈54 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

No advisories in OSV for agenthub-multiagent-mcp@1.78.1 as of 20 h ago. This is the package itself, not its dependencies.