Skills/npm/mcp-server

mcp-server@0.45.119

CAUTION· not started

Publisher claims: "Typeroll CMS MCP server – connect AI agents to the REST API to manage content and publish static websites." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher typeroll · publishing for 173 daysInstalls 15,251Last detonated 7d ago
What would fix thisWatchDispute verdict

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: 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-server` runs it now and prints the full answer.

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 2026-11-07 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.8sprocessdependency install exit 1
0.9sprocessexec /usr/bin/date
0.9sprocessexec /usr/bin/timeout
0.9sclaimedno tools/list reply (exit 0)
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/bundled-content.js:17 · File type combined with upload action — agent may exfiltrate local data files"tr-import-url": "---\nname: tr-import-url\ndescription: Use when the user wants to import or migrate content from a non-WordPress website — a Squarespace site, a Wix site, a static HTML site, a WebflFix: 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 packagedist/install-skills.js:121 · npx invocation of non-well-known package — may execute untrusted codeconsole.error('Usage: npx @typeroll/mcp-server install-skills <destination> [--force]');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsskills/tr-imagegen.md:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`.env` keys (only the ones the user has — check before assuming):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/tools/domain.js:122 · Auto-update or dynamic fetch configuration — agent may load new code at runtimename: 'set_organization_build_auto_update', noSite: true,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/workspace.js:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexport const ignores = ['.typeroll/', '.env', '.env.*', '!.env.example', '.mcp.json', '.cursor/mcp.json', '.vscode/mcp.json', 'qa/reports/', 'sources/private/', '**/__pycache__/', 'scripts/typeroll/noFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Text pushed off-screen by whitespaceskills/tr-migration-evidence.md:225 · Text pushed off-screen by whitespace| Only with the owner's approval, in `cookie_consent.scripts_optional` with the banner enabled. Never in `scripts_head`, `scripts_body_end`, `scripts_necessary`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)dist/bundled-content.js:22 · MCP server using network transport (SSE/HTTP) — data sent over network"tr-new-site": "---\nname: tr-new-site\ndescription: Use when the user wants to create a new Typeroll site from scratch, set up the initial design, or bootstrap a blank site with working header/footerFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathsskills/tr-imagegen.md:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesLoad them per-command (`source .env` doesn't persist between Bash calls):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Text pushed off-screen by whitespaceskills/tr-migration-evidence.md:223 · Text pushed off-screen by whitespace| Never copy. Enable the site's cookie banner (`cookie_consent.enabled: true`) with Swedish or local text and the privacy policy URL. |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiondist/bundled-content.js:19 · File type combined with upload action — agent may exfiltrate local data files"tr-migrate-multisite": "---\nname: tr-migrate-multisite\ndescription: Use when migrating SEVERAL sites at once — a WordPress multisite network, a group of country/language sites on different top-leveFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/bundled-content.js:15 · File type combined with upload action — agent may exfiltrate local data files"tr-imagegen": "---\nname: tr-imagegen\ndescription: Use when the user wants to generate images for a Typeroll site with AI models (Gemini, OpenAI, Higgsfield) — hero images, illustrations, section baFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsskills/tr-imagegen.md:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslive in the folder's `.env`, candidates land in `images/lab/`, and onlyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/tr-imagegen.md:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexport $(grep -v '^#' .env | xargs) # prepend to each generation commandFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsskills/tr-imagegen.md:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files├── .env # provider keys — GITIGNORED, never committedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/tools/domain.js:105 · Auto-update or dynamic fetch configuration — agent may load new code at runtimedescription: 'Read the selected provider, saved Cloudflare and GitHub build engines, and active jobs for the organization (each with job_id, site_id, kind and status: queued, running, or publishing whFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/bundled-content.js:20 · File type combined with upload action — agent may exfiltrate local data files"tr-migrate-wp": "---\nname: tr-migrate-wp\ndescription: Use when the user asks to migrate a WordPress site to Typeroll, mentions wp-json, or names a WP source URL. Walks the WP REST API, preserves clFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/bundled-content.js:64 · MCP server using network transport (SSE/HTTP) — data sent over network"agents": "# AGENTS.md — Working on a Typeroll site\n\nYou are connected to a Typeroll site through `@typeroll/mcp-server`.\nThis file is your briefing: what the system is, what conventions matter,\nwFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actiondist/bundled-content.js:26 · File type combined with upload action — agent may exfiltrate local data files"tr-seo": "---\nname: tr-seo\ndescription: Use before a site's first launch and whenever the user asks to improve SEO, fix titles or meta descriptions, set a share image, add structured data, check thFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/bundled-content.js:65 · MCP server using network transport (SSE/HTTP) — data sent over network"readme": "# Typeroll CMS MCP server\n\nThe `@typeroll/mcp-server` package connects MCP-compatible AI clients to the\n[Typeroll CMS](https://typeroll.com) public API. Manage sites through tools to reaFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Text pushed off-screen by whitespaceskills/tr-migration-evidence.md:222 · Text pushed off-screen by whitespace| Never copy. Rebuild what it did with native blocks, Forms or settings, or report a platform gap (see "Report platform gaps"). |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/bundled-content.js:65 · npx invocation of non-well-known package — may execute untrusted code"readme": "# Typeroll CMS MCP server\n\nThe `@typeroll/mcp-server` package connects MCP-compatible AI clients to the\n[Typeroll CMS](https://typeroll.com) public API. Manage sites through tools to reaFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/bundled-content.js:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"tr-imagegen": "---\nname: tr-imagegen\ndescription: Use when the user wants to generate images for a Typeroll site with AI models (Gemini, OpenAI, Higgsfield) — hero images, illustrations, section baFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/tools/migration.js:91 · File type combined with upload action — agent may exfiltrate local data filesdescription: "Add old-site URLs to the inventory in bulk (up to 2000 per call). This is how the inventory gets populated outside the in-portal WordPress migration: walk the old sitemap.xml, a GSC expoFix: 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 packageskills/README.md:20 · npx invocation of non-well-known package — may execute untrusted codenpx @typeroll/[email protected] init ./my-site --recipes --updateFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/tools/settings.js:68 · File type combined with upload action — agent may exfiltrate local data filesai_crawler_policy: z.enum(['allow_all', 'no_training', 'block_all']).nullable().optional().describe('AI crawler preference, written as Cloudflare-compatible Content Signals in robots.txt and the ConteFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/workspace.js:119 · MCP server using network transport (SSE/HTTP) — data sent over network'README.md': `# Website workspace\n\nKeep project intent here; edit the website through Typeroll CMS.\n\n1. Read AGENTS.md. For guidance, ask your agent to start or resume workflows/interview.md. OtheFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packageskills/README.md:19 · npx invocation of non-well-known package — may execute untrusted codenpx @typeroll/[email protected] init ./my-site --recipesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/workspace.js:119 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file'README.md': `# Website workspace\n\nKeep project intent here; edit the website through Typeroll CMS.\n\n1. Read AGENTS.md. For guidance, ask your agent to start or resume workflows/interview.md. OtheFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/workspace.js:119 · npx invocation of non-well-known package — may execute untrusted code'README.md': `# Website workspace\n\nKeep project intent here; edit the website through Typeroll CMS.\n\n1. Read AGENTS.md. For guidance, ask your agent to start or resume workflows/interview.md. OtheFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈23,069 tok
2 files · 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 @typeroll/mcp-server@0.45.119 as of 7d ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim typeroll: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. 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 typerollPropose a patch to the maintainer