DesignDiff MCP
Verifies that AI-generated UI code matches Figma design specs by rendering components in a real browser, comparing computed CSS, and returning patch-ready fixes with scored parity reports.
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
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
Valkyrie2048
Source: Glama
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.
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.
audit_state_coverageCheck whether every interactive state defined in a Figma component actually exists in code. Figma components define states as variants (State=Hover, State=Focus, State=Disabled, etc.). This tool extracts every state from the Figma COMPONENT_SET, attempts to trigger it in the headless renderer, and …
check_component_parityCompare a Figma design spec against live rendered code. Returns a scored parity report with: • Visual Fidelity — computed browser styles vs Figma spec (spacing, color, typography, borders) • Source Compliance — AST scan of source file for hardcoded values bypassing design tokens • State Coverage — …
check_responsive_parityRender a component at multiple viewport widths and detect layout, spacing, and visibility issues that only appear at specific breakpoints. Catches the most common mobile implementation gap: designers provide responsive variants in Figma, developers implement desktop-only. This tool renders at each …
check_theme_parityRun parity checks across multiple Figma variable modes (light/dark, brand variants, high-contrast). Catches token drift that only surfaces in a specific theme — the most common: dark mode where a hardcoded hex looks fine in light but becomes invisible on a dark background. Renders the component wit…
flag_stale_mappingsAudit all Code Connect mappings in a Figma file for drift. Returns components where design has changed after the connected code file was last updated — ranked by severity, impact, and days since divergence. Reads from .figma/code-connect.json in your repo root. Returns actionable summary with speci…
generate_sync_patchGenerate a targeted patch to fix parity mismatches between Figma design and live code. This tool first runs a parity check (same as check_component_parity), then generates the minimum set of changes required to close the gap. It does NOT rewrite the component — it produces surgical fixes only: the …
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
FIGMA_API_KEY"env": { "": "your-token-here" }TRANSPORTstdio stdio or httpPORTDependencies
9 dependencies, 1 flagged: playwright
All four hints declared on every tool
5/6 tools missing one or more hints — audit_state_coverage (missing: idempotentHint, openWorldHint); check_component_parity (missing: idempotentHint, openWorldHint); check_responsive_parity (missing: idempotentHint, openWorldHint), +2 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.
Tool inputs are validated
Only 0/6 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
3 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 18 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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.
[](https://m8ven.ai/mcp/valkyrie2048/designdiff)?variant=verified from the URL.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