Skills/Glama/mcpfinder

mcpfinder@0.1.0

CAUTION· install only

Publisher claims: "Enables searching and filtering a directory of over 34,000 MCP servers by keyword, category, language, and hosting type, then generates ready-to-paste configuration for Claude Desktop, Cursor, Windsurf, Zed, and Claude Code. Also lets an AI assistant discover and recommend servers conversationally and produce their install configs." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher jaeyunkim62 · publishing for 1 daysInstalls 0Last detonated 14 h ago
What would fix thisWatchDispute verdict

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: Caution 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
API_KEYGITHUB_TOKENConfiguration, not credentials: OUT_PATH
Where it talks to
no vendor host named in the codeAlso githubusercontent.com, acme.dev, vitejs.dev — 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 githubusercontent.com, acme.dev, vitejs.dev as well as its own vendor. The guard injects API_KEY, GITHUB_TOKEN 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 2026-11-13 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Prompting user to enter sensitive credentials. 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
Auto-update or dynamic fetch configurationsrc/i18n/index.ts:74 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeremoteConfigNotice: 'Remote endpoint configuration',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Prompting user to enter sensitive credentialssrc/i18n/index.ts:86 · Prompting user to enter sensitive credentials — social engineeringenvVarsNotice: 'Enter your credentials below. They are rendered directly into the configuration snippet locally and never leave your browser.',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
MCP server using network transport (SSE/HTTP)src/utils/configGenerator.test.ts:41 · MCP server using network transport (SSE/HTTP) — data sent over networkassert.deepEqual(JSON.parse(get('windsurf')).mcpServers['acme-db-mcp'], { serverUrl: 'https://mcp.acme.dev/sse' });Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagescripts/merge.ts:115 · npx invocation of non-well-known package — may execute untrusted code: `npx -y ${pkg.identifier}`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/i18n/featured-translations.json:103 · MCP server using network transport (SSE/HTTP) — data sent over network"codelogicincengineering/codelogic-mcp-server": "Developer Tools 작업 도구로, CodeLogic code dependency 데이터 분석 및 통계, architectural risk analysis and impact assessment.",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagedata/manual.json:4 · npx invocation of non-well-known package — may execute untrusted code"install": "npx -y github:TaewoooPark/Trendchaser-mcp"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedata/manual.json:8 · npx invocation of non-well-known package — may execute untrusted code"install": "npx -y @notionhq/notion-mcp-server"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/merge.ts:310 · npx invocation of non-well-known package — may execute untrusted codeinstallCommand: `npx -y ${entry.packageName}`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/utils/configGenerator.test.ts:39 · MCP server using network transport (SSE/HTTP) — data sent over networkassert.deepEqual(JSON.parse(get('claude')).mcpServers['acme-db-mcp'], { command: 'npx', args: ['-y', 'mcp-remote', 'https://mcp.acme.dev/sse'] });Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)src/i18n/featured-translations.json:146 · MCP server using network transport (SSE/HTTP) — data sent over network"extentos/mcp-server": "Build smart-glasses apps 솔루션으로, scaffold, validate and simulate Meta smart glasses integrations (camera capture, voice, audio) in Android and iOS apps.을(를) 지원합니다.",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Authorization escalation languagesrc/i18n/featured-translations.json:19 · Authorization escalation language · informational: not an instruction file"krovacloud/krova-node": "Cloud Platforms 작업 도구로, Provision and manage Krova Cloud Cubes (Firecracker microVMs with root access), plus custom domains, TCP port mappings and snapshots.",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)src/i18n/featured-translations.json:203 · MCP server using network transport (SSE/HTTP) — data sent over network"jsdelivr/globalping-mcp-server": "ping, traceroute, mtr, HTTP and DNS measurements from locations around the world via Globalping 관련 실행 기능을 지원합니다.",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagesrc/utils/configGenerator.test.ts:13 · npx invocation of non-well-known package — may execute untrusted codeassert.deepEqual(parseInstallCommand({ ...base, cmd: 'npx -y @acme/db-mcp --ro' }), { command: 'npx', args: ['-y', '@acme/db-mcp', '--ro'] });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/utils/configGenerator.test.ts:40 · MCP server using network transport (SSE/HTTP) — data sent over networkassert.deepEqual(JSON.parse(get('cursor')).mcpServers['acme-db-mcp'], { url: 'https://mcp.acme.dev/sse' });Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagescripts/merge.ts:344 · npx invocation of non-well-known package — may execute untrusted codeinstallCommand: `npx -y ${entry.packageName}`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈35 tok
1 file · 49 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.

What would make this Verified

6 points 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 jaeyunkim62: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  5. 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 Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jaeyunkim62Propose a patch to the maintainer