Skills/npm/mcp

mcp@0.113.0

CAUTION

Publisher claims: "Anychat MCP server — drive your Anychat workspace (agents, playbooks, channels, people, outreach) from Claude Code, Claude Desktop, Cursor, or any MCP host." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher anychat-ai · publishing for 91 daysInstalls 6,949Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Started with a decoy ANYCHAT_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ANYCHAT_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
ANYCHAT_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
ANYCHAT_API_KEYConfiguration, not credentials: ANYCHAT_API_URL, ANYCHAT_DOCS_URL
Where it talks to
anychat.ai (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for ANYCHAT_API_KEY and talks to anychat.ai. 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 ANYCHAT_API_KEY=anychat.ai -- npx -y @anychat-ai/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 2026-11-11 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 50 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
9.7sprocessdependency install exit 0
30sprocessrelaunched with a decoy ANYCHAT_API_KEY (tagged; nothing real)
50sclaimed247 tools with a decoy ANYCHAT_API_KEY: whoami, list_agents, get_agent, create_agent, update_agent, delete_agent, export_agent, import_agent, apply_agent_template, get_template_update, preview_template_update, apply_template_update, list_catalog_items, get_catalog_item, get_identity, update_identity, get_personality, set_personality, import_personality_template, get_standing_instructions, set_standing_instructions, get_guardrails, set_guardrails, update_guardrails, import_guardrail_template
50sprocessscript backend runs setup only
50sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationdist/tools/channels.js:138 · Credential pass-through configuration — agent relays sensitive credentials…lack, viber, poe → bind_channel); 422 for a value Google does not accept. Never pass credentials. Maps to POST /v1/orgs/{org}/agents/{agent}/channels with mode "managed".', …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
CRITICAL
Prompting user to enter sensitive credentialsdist/tools/ajo.js:90 · Prompting user to enter sensitive credentials — social engineering…, response, errorResponse }, runbook[] (setup and branching steps, in order) }. Paste your API key (scope integrations:ajo) in place of the Authorization placeholder. 422 agent.o…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
npx invocation of non-well-known packagedist/bin.js:7 · npx invocation of non-well-known package — may execute untrusted code* ANYCHAT_API_KEY=sk-any-... npx -y @anychat-ai/mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈74 tok
1 file · 62 in bundle
Tool list per prompt
≈81,196 tok
247 tools · 329 per tool
Handshake
4774 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 473

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 @anychat-ai/mcp@0.113.0 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim anychat-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim anychat-aiPropose a patch to the maintainer