Skills/Glama/vcf-automation-mcp

vcf-automation-mcp@0.2.1

VERIFIED· install only

Publisher claims: "Enables MCP clients to call VCF Automation 9 REST operations as individual tools across 16 services, including deployments, catalog items, blueprints, policies, and IaaS resources. It also supports service-account setup, automatic token refresh, read-only filtering, and selective service loading." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher imtrinity94 · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add vcf-automation-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
VCFA_API_TOKENVCFA_AUTH_MODEVCFA_BEARER_TOKENVCFA_PASSWORDVCFA_REFRESH_TOKENVCFA_TOKENVCFA_TOKEN_FILEConfiguration, not credentials: GEN_MAX_DEPTH, VCFA_CLIENT_ID, VCFA_CLOUDAPI_VERSION, VCFA_DOMAIN, VCFA_EXCLUDE_SERVICES, VCFA_HOST, VCFA_INSECURE, VCFA_MAX_RESPONSE_CHARS, VCFA_ORG, VCFA_READ_ONLY, VCFA_SERVICES, VCFA_TENANT, VCFA_TIMEOUT_MS, VCFA_TOOL_FILTER, VCFA_URL, VCFA_USERNAME
Where it talks to
no vendor host named in the codeAlso vmw.lab, example.lab — 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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names vmw.lab, example.lab as well as its own vendor. The guard injects VCFA_API_TOKEN, VCFA_AUTH_MODE, VCFA_BEARER_TOKEN, VCFA_PASSWORD, VCFA_REFRESH_TOKEN, VCFA_TOKEN, VCFA_TOKEN_FILE only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 81/100 (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 · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
URL with embedded credentialsspecs/Event Broker.json:1 · URL with embedded credentials — may be phishing or credential leaking…ding access to operations with Event Broker.","contact":{"name":"VMware","url":"https://www.vmware.com/","email":"[email protected]"},"license":{"name":"Copyright (c) 2025 Broadcom, Inc. All Rights Res…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Credential pass-through configurationspecs/Provider Management.json:4905 · Credential pass-through configuration — agent relays sensitive credentials"x-vcloud-restricted" : "Proxy tokens are visible only to the owner of the token. Extension tokens are visible only on creation."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)specs/Project Service.json:520 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileТheFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsrc/setup.ts:327 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Windows: if the client still cannot find it, run "where vcf-automation-mcp" and put that full path');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known package.github/social-preview.html:82 · npx invocation of non-well-known package — may execute untrusted code<div class="foot"><code>npx vcf-automation-mcp</code><span>github.com/imtrinity94</span></div>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languagespecs/Content Form.json:1933 · Authorization escalation language · informational: not an instruction file"description" : "'Forbidden' when the user has no admin access rights."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstest/run-tests.mjs:101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { PATH: process.env.PATH, HOME: TMP, USERPROFILE: TMP, VCFA_HOST: HOST, VCFA_ORG: ORG, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languagespecs/Content Form.json:1416 · Authorization escalation language · informational: not an instruction file"description" : "'Forbidden' when the user has no admin access rights."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagespecs/Content Form.json:846 · Authorization escalation language · informational: not an instruction file"description" : "'Forbidden' when the user has no admin access rights."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)specs/Project Service.json:565 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileТheFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagespecs/Content Form.json:1320 · Authorization escalation language · informational: not an instruction file"description" : "'Forbidden' when the user has no admin access rights."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈42 tok
1 file · 31 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.