Skills/npm/mcp

mcp@0.2.6

VERIFIED

Publisher claims: "Model Context Protocol (stdio) server for AgentChain Agent API v1 — same REST contract and auth as OpenAPI." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher agentchainlabsai · publishing for 22 daysInstalls 1,514Last detonated 4d ago
$claude mcp add mcp -- npx -y @agentchainlabsai/mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
AGENTCHAIN_API_KEYPRIVATE_KEYConfiguration, not credentials: AGENTCHAIN_BASE_URL, AGENTCHAIN_LANG, AGENTCHAIN_LOCALE, AGENTCHAIN_MCP_TOOLSETS
Where it talks to
agentchainlabs.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for AGENTCHAIN_API_KEY, PRIVATE_KEY and talks to agentchainlabs.com. 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.

$vet-skills run --secrets AGENTCHAIN_API_KEY=agentchainlabs.com,PRIVATE_KEY=agentchainlabs.com -- npx -y @agentchainlabsai/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) on 2026-11-10 and scored it 83/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.2sprocessdependency install exit 0
24sclaimed70 tools: load_playbook_skill, agent_playbook, get_agent_wake, wait_for_events, ack_events, upload_media, ask_about_job, send_order_message, rate_buyer, list_wallet_transactions, get_daily_limit, get_autonomy_status, get_wallet_funding, rate_job, get_trust_progress, list_pending_ratings, list_notifications, mark_notifications_read, agent_discovery, fetch_openapi_spec, multipart_upload_note, agent_me, list_job_categories, browse_marketplace_jobs, browse_marketplace_gigs
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationsrc/create-server.js:43 · Credential pass-through configuration — agent relays sensitive credentials* persistRelayApiKey?: boolean;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
npx invocation of non-well-known packagesrc/create-server.js:3397 · npx invocation of non-well-known package — may execute untrusted code'npx -y @agentchainlabsai/cli auth register --private-key $PRIVATE_KEY --agree-terms --name "My Agent"',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Credential pass-through configurationsrc/create-server.js:61 · Credential pass-through configuration — agent relays sensitive credentialsconst persistRelayApiKey = options.persistRelayApiKey !== false;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
npx invocation of non-well-known packagesrc/create-server.js:3396 · npx invocation of non-well-known package — may execute untrusted code'npx -y @agentchainlabsai/cli wallet create',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/create-server.js:34 · npx invocation of non-well-known package — may execute untrusted code…an run background tasks or monitors (Grok Build, Claude Code and similar), run `npx -y @agentchainlabsai/cli listen` with AGENTCHAIN_API_KEY set under a monitor: ever…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Credential pass-through configurationsrc/create-server.js:3280 · Credential pass-through configuration — agent relays sensitive credentialsif (persistRelayApiKey && typeof data?.apiKey === 'string' && data.apiKey.startsWith('ag_')) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/create-server.js:3298 · Credential pass-through configuration — agent relays sensitive credentials? persistRelayApiKeyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/index.js:24 · Credential pass-through configuration — agent relays sensitive credentialspersistRelayApiKey: true,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02

Cost to the agent

Instructions loaded
≈63 tok
1 file · 12 in bundle
Tool list per prompt
≈10,789 tok
70 tools · 154 per tool
Handshake
969 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 221

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 @agentchainlabsai/mcp@0.2.6 as of 4d ago. This is the package itself, not its dependencies.