vishwakarma (yogvidwankhede/vishwakarma) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 14 tools. No publisher has claimed this listing.

D
Caution
56/100

vishwakarma

Design intelligence and engineering discipline for AI coding agents. 32 skills, 515 rules — every one with its mechanism stated. Computed OKLCh colour, intent-derived motion, platform-correct constants for web, Android and Apple, and an always-on working discipline.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

yogvidwankhede

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
// tools this server exposes14 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_skills

List every available Vishwakarma skill with its id, category, trigger description, and context cost. Call this to see what guidance exists before deciding what to load.

search_skills

Find the skills relevant to what you are about to do. Describe the task in your own words — for example "building a pricing page with animated cards" — and this returns the skills that apply, ranked. Call this first, before writing any interface code.

get_skill

Retrieve the full working knowledge of one skill: its body, its normative rules with the reasoning behind each, and the self-checks to run before reporting completion.

get_skill_reference

Retrieve deep reference material attached to a skill — edge cases, catalogues, worked examples. Only fetch one when its stated question is the question you actually have.

check_contrast

Compute the contrast between a foreground and background colour, and report whether it meets accessibility requirements. Use this instead of estimating — contrast is arithmetic, and estimates are unreliable in the mid-tones where most failures happen.

build_palette

Generate a perceptually even colour ramp from a single seed colour, in OKLCh. Produces the 50–950 steps with lightness spaced by perception rather than by arithmetic, chroma shed toward the ends, and every step gamut-mapped without hue drift.

resolve_motion

Turn a semantic motion intent into concrete duration, easing, and CSS. Choose the intent by what the motion means, not by how long you want it to take — the timing follows from the meaning.

check_animation_property

Report whether a CSS property can be animated on the compositor or forces layout every frame, with a concrete alternative when it does.

compute_stagger

Compute per-element delays for a group reveal, with automatic compression so a long list still reads as one gesture rather than a queue.

design_direction

Resolve a deterministic set of design decisions — hero composition, section rhythm, emphasis strategy, accent discipline, motion character — from the brief. Call this BEFORE designing anything. It exists to stop the design collapsing onto the most predictable option, which is what makes generated wo

fluid_size

Build a CSS clamp() that scales a value with viewport width. Retains a rem term so the result still respects the user’s browser font-size setting, which a pure vw value would ignore.

viewport_checklist

Return the viewport configurations to verify against, and exactly what to check at each. Use this instead of asking whether something "is responsive", which is not a checkable question.

audit_design

Evaluate measurements taken from an interface against the project Design Contract, and return specific violations with fixes. Extract the actual values from your output and pass them here rather than judging by impression.

get_tokens

Generate a complete design token set in the requested format. Supply a brand colour to derive the whole system from it, including a dark theme that is a separate design rather than an inversion.

// known CVEs in dependencies1 critical3 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.0GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.18.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.18.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.18.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

lowvitest@3.2.0GHSA-82fw-gwwq-j7x9

Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

14/14 tools missing one or more hints — list_skills (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_skills (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_skill (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.18.0 (high), @modelcontextprotocol/sdk@1.18.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Domain consistency

npm scope @vishwakarma doesn't match GitHub owner yogvidwankhede

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/yogvidwankhede/vishwakarma?variant=verified)](https://m8ven.ai/mcp/yogvidwankhede/vishwakarma)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 18acd47ab905481a05af3f71a9b8aae4ae866d9a
code hash: 56bd08e7347b453767551232fa71a989b33d90d8d215ceecf9825b9bd54511a8
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client