Rams
REMOTE · WORKER.RAMS.AI
Design review for UI code and live pages: quick checks, 0-100 scored reviews, fixes as patches
Available components
Last scanned (11 hours ago)
Scores higher than 99% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1329 tokens (~265/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
- Stability: 0.97 → pass security
- 4 Nov 26 −1
- Stability: pass → 0.97 functional
- 15 Oct 26 0
- Tool coverage: 40% → 100% ▲ functional
- Tool “quick_review” now declares an output schema ▲ functional
- Tool “review_url” now declares an output schema ▲ functional
- Tool “usage” now declares an output schema ▲ functional
- 9 Oct 26 0
- Tool coverage: 50% → 40% ▼ functional
- Schema quality: 207 → 265 ▼ functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “quick_review” rewrote its description, which is the text the model reads security
- 20 Sept 26 0
- Schema quality: 182 → 204 ▼ functional
- “quick_review” added an optional parameter “via” cosmetic
- “review_files” added an optional parameter “via” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://worker.rams.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=worker.rams.ai | CN=WR3,O=Google Trust Services,C=US | 22 Oct 2026 | 20 Jan 2027 | RSA 2048 | SHA256-RSA | 238f5e616d18b6a109f14a7bd254805c |
| SANs: worker.rams.ai | ||||||
| CN=WR3,O=Google Trust Services,C=US (CA) | CN=GTS Root R1,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | RSA 2048 | SHA256-RSA | 7ff005a91568d63abc22861684aa4b5a |
| CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 19 Jun 2020 | 28 Jan 2028 | RSA 4096 | SHA256-RSA | 77bd0d6cdb36f91aea210fc4f058d30d |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of worker.rams.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814, 3799 | 8, 8 | Verified |
| rams.ai. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://worker.rams.ai/.well-known/oauth-protected-resource/mcp"
Bearer resource_metadata="https://worker.rams.ai/.well-known/oauth-protected-resource/mcp"| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self';base-uri 'self';font-src 'self' https: data:;form-action 'self';frame-ancestors 'self';img-src 'self' data:;object-src 'none';script-src 'self';script-src-attr 'none';style-src 'self' https: 'unsafe-inline';upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
Protected resource metadata
| Document | https://worker.rams.ai/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://worker.rams.ai/mcp |
| Authorisation server | https://worker.rams.ai |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://worker.rams.ai/mcp | Verified | 200 | |
| http (plaintext) | http://worker.rams.ai/mcp | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
quick_review Rams quick check ~279
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Short label, e.g. the component or feature name |
| files | array | yes | The UI code, one entry per file (up to 20): the real path, or for pasted code a path that fits it (pasted/Card.tsx), and the full code |
| via | string | – | Set to "rules" when this call is made because of a standing instruction in a rules file (e.g. CLAUDE.md). Omit when a person asked for the review. |
| Name | Type | Req | Description |
|---|---|---|---|
| issueCount | number | yes | – |
| issues | array | yes | – |
| message | string | – | Present when ran is false: the reason, in words |
| ran | boolean | yes | false when the check did not run (hourly limit, no credits left, engine failure) or came back unusable; message says why |
No examples provided.
review_files Rams design review ~281
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Short label for this review, e.g. the feature or branch name |
| files | array | yes | The UI code, one entry per file (up to 20): the real path, or for pasted code a path that fits it (pasted/Card.tsx), and the full code |
| via | string | – | Set to "rules" when this call is made because of a standing instruction in a rules file (e.g. CLAUDE.md). Omit when a person asked for the review. |
| Name | Type | Req | Description |
|---|---|---|---|
| detectedCounts | object | yes | – |
| direction | string | – | What the change is trying to be — judgment before findings |
| issues | array | yes | – |
| reviewsLimit | number|null | yes | null = unlimited (Team overage applies instead) |
| reviewsUsed | number | yes | – |
| score | number | yes | 0-100; confirmed criticals cap it — one at 59, two at 49, three or more at 39 |
| summary | string | yes | – |
| visualFindings | array | – | Findings seen in a render of the code, each with a crop URL |
| visualPair | object | – | One verified before/after of the top fix (image URLs), when one was rendered |
No examples provided.
review_url Rams page review ~215
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.
| Name | Type | Req | Description |
|---|---|---|---|
| focus | string | – | Optional: what to put first, e.g. "mobile", "typography", "color" |
| url | string | yes | The page to review, e.g. https://rams.ai or rams.ai/pricing |
| Name | Type | Req | Description |
|---|---|---|---|
| detectedCounts | object | yes | – |
| findings | array | yes | Every finding, most severe first (the text shows the top 8) |
| host | string | yes | The page that was reviewed (host only) |
| reviewsLimit | number|null | yes | null = unlimited |
| reviewsUsed | number | yes | – |
| score | number | yes | 0-100, what a designer sees in the two screenshots; one critical caps it at 59 |
| scores | object | yes | – |
| summary | string | yes | – |
No examples provided.
usage Rams review quota ~33
Check how many Rams reviews this account has used and how many are left. Free to call. It does not use a review.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| fullReviews | object | – | Present when full reviews are capped; past the cap review_files returns a quick check |
| limit | number|null | yes | Review credits included; null = unlimited |
| overageBilling | boolean | – | Present where it applies: true = reviews past the limit keep running and are billed on the monthly invoice |
| pausedNow | boolean | – | An account set to pause at its limit: true while paused |
| plan | string | – | Plan name |
| purchasedCredits | number | yes | Purchased review credits, spent automatically once the included ones run out |
| remaining | number|null | yes | Included credits left; null = unlimited |
| resumesAt | string | – | An account set to pause at its limit: when the next billing cycle starts (ISO 8601) |
| used | number | yes | Review credits used in the window |
| window | string | yes | "lifetime" (free reviews that do not renew), "billing_cycle" (an account set to pause at its limit) or "rolling_30_days" |
No examples provided.
verify_fixes Verify Rams fixes landed ~102
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.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | The updated UI files (same paths as the original review) |
| issues | array | yes | The findings to verify, as returned by review_files |
| Name | Type | Req | Description |
|---|---|---|---|
| allClear | boolean | yes | true when nothing remains, including no remaining criticals |
| fixed | array | yes | – |
| present | array | yes | – |
No examples provided.
How do I install the Rams MCP server?
Rams is a hosted endpoint at https://worker.rams.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · worker.rams.ai
claude mcp add --transport http ai-rams-rams 'https://worker.rams.ai/mcp'
What is the Rams MCP server?
Rams is an MCP server listed in the public MCP registry as ai.rams/rams. Design review for UI code and live pages: quick checks, 0-100 scored reviews, fixes as patches. This page covers its hosted endpoint (https://worker.rams.ai/mcp).
Is the Rams MCP server safe to use?
Rams scores 92 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Rams MCP server expose?
Rams exposes 5 tools: usage, review_files, quick_review, verify_fixes, review_url. Their descriptions and schemas cost roughly 910 tokens of context every time the server is loaded.
Does the Rams MCP server require authentication?
Yes. Rams asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Rams MCP server still maintained?
Rams is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Rams MCP server?
VerifyMCP ran 13 checks on Rams, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.