Skills/npm/mcp-server

mcp-server@1.30.0

VERIFIED

Publisher claims: "MCP Server for Regle" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher regle · publishing for 343 daysInstalls 670Last detonated 18 h ago
$claude mcp add mcp-server -- npx -y @regle/mcp-server
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
no credential variables read in the code
Where it talks to
reglejs.dev (its own)Also standardschema.dev, vuejs.org, stackblitz.com, skills.sh, cursor.com, zod.dev, valibot.dev, arktype.io, tanstack.com, vitejs.dev, typescriptlang.org, visualstudio.com, nuxt.com, posthog.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it under the guard; read the third-party hosts first. The code names standardschema.dev, vuejs.org, stackblitz.com, skills.sh, cursor.com, zod.dev, valibot.dev, arktype.io, tanstack.com, vitejs.dev, typescriptlang.org, visualstudio.com, nuxt.com, posthog.com as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- npx -y @regle/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.29.5

vet-skills diff mcp-server 1.29.5 1.30.0

In the sandbox, this version reached for nothing 1.29.5 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-19 and scored it 82/100 (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 · 35 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
14sprocessdependency install exit 0
34sclaimed11 tools: regle-list-documentation, regle-get-documentation, regle-get-usage-guide, regle-get-vuelidate-migration-guide, regle-search-documentation, regle-list-rules, regle-get-rule-reference, regle-list-validation-properties, regle-list-helpers, regle-get-helper-reference, regle-get-api-reference
34stools7860164d3276272f
34stoolsabc92eaf96b88ef9
34stoolsdad24f0c1f5410fc
34stoolsdad24f0c1f5410fc
34stools06834296ccd3fb7e
34stoolsdad24f0c1f5410fc
34stools0cde40bb2413c6bd
34stoolsdad24f0c1f5410fc
34stoolsdad24f0c1f5410fc
34stools50af10794844fa34
34stools4861c373ed39ff0e
34sprocessscript backend runs setup only
34sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/regle-mcp-server.js:309 · npx invocation of non-well-known package — may execute untrusted code… walks an AI coding agent through this migration step by step. Install it with `npx skills add victorgarciaesgi/regle`.\n:::\n\n## Imports\n\n```ts\nimport { useVuelidate…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/regle-mcp-server.js:106 · File type combined with upload action — agent may exfiltrate local data files…\n})\n\nconst result = await r$.['~standard'].validate({ name: '' });\n\nconsole.log(result.issues);\n```\n\n### Schema only usage\n\n```ts\nimport { useRules } from '@regle/core';\nimport { required, string } from '@regle/rules';\n\nconst…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Prompting user to enter sensitive credentialsdist/regle-mcp-server.js:43 · Prompting user to enter sensitive credentials — social engineering…ssword\"\n :class=\"{ valid: r$.password.$correct }\"\n placeholder=\"Type your password\"\n />\n\n <button type=\"button\" @click=\"r$.$reset({toInitialState: tr…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File type combined with upload actiondist/regle-mcp-server.js:71 · File type combined with upload action — agent may exfiltrate local data files…\n const {valid, data} = await r$.$validate()\n \n if (!valid) {\n console.log('Form has errors')\n return\n }\n \n // Submit data\n try {\n await submitForm(data)\n r$.$reset() // Reset form after success\n } catch (error) {\n // Handle s…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/regle-mcp-server.js:274 · File type combined with upload action — agent may exfiltrate local data files… {\n const { valid, data } = await r$.$validate();\n if (valid) {\n console.log(data);\n }\n}\n\n```\n\n```ts [Valibot]\nimport { useRegleSchema, inferSchema } from '@regle/schemas';\nimport * as v from 'valibot';\nimport { ref, computed }…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/regle-mcp-server.js:323 · File type combined with upload action — agent may exfiltrate local data files…d, data, errors, issues } = await r$.$validate();\n\n if (valid) {\n console.log(data);\n \n }\n}\n```\n\n<br/>\n\n### `InferSafeOutput`\n\nYou can also statically infer the safe output from any `r$` instance.\n\n```ts twoslash\nimport { r…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈42 tok
1 file · 6 in bundle
Tool list per prompt
≈641 tok
11 tools · 58 per tool
Handshake
576 ms
launch to tools/list, stdio
Undocumented tools
11
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 @regle/mcp-server@1.30.0 as of 18 h ago. This is the package itself, not its dependencies.

mcp-server@1.30.0 safety verdict: Verified — KillerSkills