harvey-design-system-mcp
A Model Context Protocol server that exposes a versioned brand package (tokens, rules, recipes, media rights, and audit gates) as resources, tools, and prompts for AI agents. It enables agents to plan and audit on-brand UI, image, motion, and video outputs while remaining read-only and credential-free.
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
thenpceo
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.
get_companion_setupRecommend the fal.ai API/MCP and HeyGen HyperFrames skills needed for Harvey image, motion, and video production, including official setup links and secret-handling guidance.
get_brand_contextReturn tokens, rules, recipes, evaluation gates, and module guidance for one Harvey capability.
compile_promptCompile a plain-language task into a Harvey-aligned production prompt for UI, still images, motion graphics, or video.
create_ui_blueprintCreate a responsive Harvey interface blueprint with content hierarchy, states, tokens, and QA requirements.
create_motion_blueprintCreate a measured Harvey motion plan. Partnership intent routes to the versioned partnership-announcement production template.
create_partnership_announcement_planCreate the source-gated 10-second Harvey partnership-announcement plan: one continuous architectural plate, masked center-out partner lockup, word-staggered goal copy, exact HyperFrames timing, identity handling, and concept-only safeguards.
create_video_production_planTurn one video request into an agent-ready Harvey production manifest with claims gates, B-roll, GPT Image and fal orchestration, a HyperFrames BRIEF.md, motion rules, provenance, and audits. This tool never runs or pays for a model.
suggest_b_rollCreate structured, on-brand professional B-roll shots and generation prompts without calling an image or video model.
create_hyperframes_briefReturn canonical product-launch-video BRIEF.md content for HyperFrames. Your AI agent of choice writes it only after hyperframes init creates the project.
audit_production_planCheck a Harvey video production manifest before paid generation. Blocks missing claim sources, cost visibility, likeness permission, package provenance, or HyperFrames routing.
audit_video_renderEvaluate evidence from your AI agent of choice inspecting an actual render. This tool does not inspect pixels itself and rejects uninspected output.
list_assetsList official, reference-only, and locally authorized font assets with explicit rights boundaries.
get_assetReturn rights metadata and, when permitted, a resource link to an official local asset. Never returns reference-only captures.
audit_brand_outputRun deterministic brand-conflict checks before full visual and factual review.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
vite: `server.fs.deny` bypass on Windows alternate paths
launch-editor: NTLMv2 hash disclosure via UNC path handling on Windows
FAL_KEYHARVEY_BRAND_PACKAGEHARVEY_BRAND_PACKAGE_SOURCEHARVEY_FONT_DIRTool 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 — get_companion_setup (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_brand_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compile_prompt (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.
Tool inputs are validated
13/14 tool handlers declare input schemas (93%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 1/14 tool handlers wrap calls in try/catch (7%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 1 high severity in production deps — vite@6.4.2 (high), vite@6.4.2 (medium)
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/thenpceo/harvey-design-system-mcp)?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