Rams
Server Details
Design review for UI code and live pages: quick checks, 0-100 scored reviews, fixes as patches
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- Rams
TDQS
Scored across 5 tools
quick_review and review_files both review UI code and could be mistaken for each other at a glance, but the descriptions explicitly contrast them (speed vs. score/patches, credit cost, when to call each) and cross-reference one another. review_url, usage, and verify_fixes each occupy a clearly separate slot (live page, quota, re-check).
All names are snake_case, which keeps the set readable. The verb pattern is mostly consistent (review_files, review_url, verify_fixes) with two deviations: quick_review leads with an adjective, and usage is a bare noun.
Five tools is well-scoped for a design-review service: fast check, full review, URL review, quota check, and fix verification. Each tool maps to a distinct workflow step with no filler.
The review lifecycle is well covered: review (three modes) → fix → verify_fixes → usage for quota. Minor gaps: no way to list or retrieve past reviews/findings, so agents must carry findings forward manually, and no image/screenshot review path (though this is stated as out of scope).
Publisher details
- Operator
- HSLA0001 Inc. (Rams) · Publisher source
- Operator website
- https://www.rams.ai
- Vendor relationship
- First-party
- Documentation
- https://www.rams.ai/mcp
- Privacy policy
- Not provided
- Trust center
- https://www.rams.ai/security
- Restrictions
- Needs a Rams account: sign in with OAuth in the browser, or send a Rams API key. The free plan includes 15 reviews to try it; more reviews need a paid plan.
Available Tools
5 toolsquick_reviewRams quick checkAInspect
Fast design and accessibility check of UI code (React, Vue, Svelte, HTML, CSS, SwiftUI). Returns the top issues with severity, category and file:line in about 10 seconds. Call it when the user pastes or uploads UI code, asks whether a design is good or accessible, or when you just wrote or changed a component, page or view. You do not need to ask first. Pass each file with its real path, or for pasted code a path that fits it (pasted/Card.tsx, pasted/index.html) and the full code. Five quick checks cost one review credit (two on the free plan). It reads code only, not screenshots or URLs. It returns no score and no patch: fix the issues yourself. For a score or patches, use review_files.
Inputs: files (required), via, context. Returns: ran, issues, message, issueCount
review_filesRams design reviewAInspect
Full Rams design review of UI code (React, Vue, Svelte, HTML, CSS, SwiftUI). Returns a 0-100 score (criticals cap it: one caps at 59, two at 49, three or more at 39), issues with severity, category, file:line, and concrete fixes as patches. Call it once at the end: before a commit, or when the user wants a score or a final check. Pass each file with its real path, or for pasted code a path that fits it (pasted/Card.tsx). Each call uses one review credit. Reviewing a few files needs no permission. Ask the user before a whole-codebase audit (dozens of files), since it spends their allowance. For quick feedback while you work, use quick_review.
Inputs: files (required), via, context. Returns: score, issues, summary, direction, +5 more
review_urlRams page reviewAInspect
Review a live public web page by its URL, no code needed. Rams opens the page at desktop (1440px) and phone (390px) widths, measures the rendered page and looks at both screenshots, then returns the top design issues (severity, category, where on the page, and a fix in plain words) with a 0-100 score. Use it when the user names a site or a page: "review rams.ai with Rams", "how does my landing page look?". It takes up to a minute and uses one review credit. Public pages only: no sign-in pages, localhost or private addresses. It returns no code patches. If the user has the code for the page, use quick_review or review_files on those files instead.
Inputs: url (required), focus. Returns: host, score, scores, summary, +4 more
usageRams review quotaARead-onlyIdempotentInspect
Check how many Rams reviews this account has used and how many are left. Free to call. It does not use a review.
Inputs: no named parameters. Returns: plan, used, limit, window, +6 more
verify_fixesVerify Rams fixes landedARead-onlyIdempotentInspect
Re-check findings from an earlier Rams review against the updated code. Pass the new version of each file under the same path as before, plus the findings. Returns fixed or still present for each one. Free: it never counts against the user's quota. Use it after you fix the issues.
Inputs: files (required), issues (required). Returns: fixed, present, allClear
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Review frontend code and live pages against 386 quality-gated web development rules.
Localization QA: find translation errors on live pages and in strings, with MQM-scored fixes.
Design review as MCP tools: critique, states, journeys, UI copy, PRD assumptions. BYOK or hosted.
Read visual design reviews from live web pages: comments, CSS selectors, styles, console errors.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceDesign review for UI code, inside your coding agent. Reviews React, Vue, Svelte, CSS and SwiftUI against 313 rules and returns scored findings with file:line fixes your agent can apply and verify.MIT

uxlintofficial
AlicenseAqualityBmaintenanceAudits any site's UX the way a design-literate reviewer would — contrast, tap targets, type scale, colour discipline, scan patterns, copy — and returns the rule, the source line and the exact fix.6Apache 2.0- AlicenseNot gradedqualityCmaintenanceSelf-hosted design audit MCP server that reviews UI code against Nielsen's heuristics and an accessibility rubric, returning scores and fixable findings. It also enables verifying previously flagged issues against updated code.97 npmBSD 3-Clause
- AlicenseAqualityBmaintenanceEnables AI agents to conduct UX reviews of web applications, detecting and fixing AI-generated design and usability issues while preserving the original style.182MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.