# UI Verify (remote · uiverify.ai)

MCP server for visual regression testing: triage a PR's UI diffs from your coding agent.

- Trust score: 72/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

> **Recent critical change**: Authorization (2026-09-17). See the changelog below before you install this server.

## Components

- remote · `uiverify.ai`: 72/100 (this document), [markdown](https://verifymcp.io/servers/igrlk-uiverify/api-mcp.md), [page](https://verifymcp.io/servers/igrlk-uiverify/api-mcp)

## Channel facts

- Endpoint: `https://uiverify.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.1`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_comment).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3416 tokens (~244/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (93% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the UI Verify MCP server?

UI Verify is a hosted endpoint at https://uiverify.ai/api/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.

### Claude

```bash
claude mcp add --transport http igrlk-uiverify 'https://uiverify.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "igrlk-uiverify": {
      "url": "https://uiverify.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "igrlk-uiverify": {
      "type": "http",
      "url": "https://uiverify.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.igrlk-uiverify]
url = "https://uiverify.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "igrlk-uiverify": {
      "type": "remote",
      "url": "https://uiverify.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add igrlk-uiverify --url 'https://uiverify.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  igrlk-uiverify:
    url: "https://uiverify.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "igrlk-uiverify": {
      "Transport": "http",
      "Url": "https://uiverify.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add igrlk-uiverify -t streamable-http -u 'https://uiverify.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "igrlk-uiverify": {
      "type": "http",
      "url": "https://uiverify.ai/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 72, +1)

- [cosmetic] “render_diff_image” added an optional parameter “pxPagination”

### 2026-09-18 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 70, 0)

- [critical regression] Authorization: unverified → fail
- [security] New tool “delete_comment”, which the server declares destructive
- [security] Tool “get_build” rewrote its description, which is the text the model reads
- [security] Tool “get_diff” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 270 → 239
- [functional] Destructive annotations: pass → 100
- [functional] New tool “list_comments”
- [functional] New tool “post_comment”
- [functional] New tool “resolve_comment”
- [functional] New tool “update_comment”

### 2026-09-16 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 67, +1)

- [security regression] A breaking change shipped without a version bump: still 0.1.0
- [security regression] Tool “get_change_attribution” was removed

### 2026-09-09 (score 66, 0)

- [functional regression] Schema quality: 2437 → 2688
- [functional] New tool “get_change_attribution”

## MCP tools (14)

### `list_builds` (~116 tokens)

List recent UI Verify builds

Recent UI Verify builds for your project, newest first. Each row is a one-line verdict (gateStatus: passed | changed | failed) for a commit/PR — use it to find the build to inspect. No image URLs or per-story detail here: call get_build for the changed-story list, get_diff for images.

Input parameters:

- `branch` (string): Only builds on this git branch.
- `limit` (integer): Max builds to return (default 20).
- `status` (string): Only builds with this raw status.

Output parameters:

- `builds` (array)

### `get_build` (~390 tokens)

Get what changed in a UI Verify build

Triage one build, resolved by commitSha, prNumber, or buildId (exactly one). Returns the gate verdict and counts (total/changed/failed/unchanged), then the FIRST page (25) of the changed stories (story id, viewport, % pixels changed, review decision, the AI verdict aiVerdict=intended|regression + aiConfidence, and for a regression the judge's one-line aiFlagReason=what-looks-unintended, when AI review is on) and the first page of failed stories (failedStories[].kind is `render` when the story produced no frame, or `interaction` when it rendered and its play() assertion threw; failedStories[].error is the message's first line, errorTruncated marks the ones that carried more). When AI review ran, aiReview tallies how many changes look like regressions vs intended, and the changed list is ordered likely-regressions-first. changedNextCursor / failedNextCursor are non-null when there are more than 25: page the rest with list_build_stories. counts.unchanged is how many stories did NOT change and have a baseline - this triage call does NOT list them (keeps the response lean); call list_build_stories status=unchanged to browse them (e.g. to confirm a passed build's stories are 'identical to baseline'). comments is the build-wide review-comment tally {total, unresolved}: unresolved>0 means a designer/QA (or another agent) left an open note on a story - read it with list_comments BEFORE you accept. No image URLs here - call get_diff or render_diff_image for pixels.

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `prNumber` (integer): Resolve the latest build for this PR number.

Output parameters:

- `aiReview`
- `autoAcceptChanges` (boolean)
- `branch` (string)
- `buildId` (string)
- `changedNextCursor` (string|null)
- `changedStories` (array)
- `comments` (object)
- `commitSha` (string)
- `counts` (object)
- `createdAt` (string)
- `failedNextCursor` (string|null)
- `failedStories` (array)
- `gateStatus` (string)
- `prNumber` (number|null)
- `status` (string)

### `list_build_stories` (~303 tokens)

Page through a build's stories by status

Page through one build's stories filtered by status (resolved by commitSha/prNumber/buildId). Use it to read past get_build's first page, or to browse the unchanged/passed stories get_build only counts. status='changed' returns changed stories (same shape + order as get_build, regression-first); status='failed' returns failed stories; status='unchanged' returns the stories that did NOT change this build but have a baseline on this branch (storyId, viewport, browser) - fetch any of their images by storyId with get_diff or render_diff_image to confirm 'identical to baseline'. Returns { stories, nextCursor }: pass nextCursor back as `cursor` for the next page; null means no more. limit defaults to 25 (max 100). Unchanged is only available once the build has settled (an in-progress build has rendered nothing, so it returns an empty page).

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `cursor` (string): The nextCursor from a prior page; omit for the first page.
- `limit` (integer): Page size (default 25, max 100).
- `prNumber` (integer): Resolve the latest build for this PR number.
- `status` (string, required): Which stories to page: changed, failed, or unchanged (baselined, didn't change this build).

Output parameters:

- `nextCursor` (string|null)
- `stories` (array)

### `get_pr_changeset` (~305 tokens)

Get what this PR does to the UI vs its base branch

The cumulative 'this PR vs base' visual changeset (resolved by commitSha/prNumber/buildId) - what the whole PR does to the UI versus the branch it merges into, INDEPENDENT of what is left to review on the latest build. Unlike get_build (this commit vs the branch's own accepted baseline), this survives in-PR accepts: a story accepted mid-PR still shows under `changed` with status=accepted, so it answers 'what did this PR change' even after the gate reads clean. Returns base (the branch it merges into), counts {new,changed,removed,unchanged}, and the first page of `new` + `changed` + `removed` stories (storyId, title, name, kind, review status, aiVerdict). `removed` lists stories that HAD a baseline on the base branch but are gone from this PR's head (a deletion - otherwise invisible; each carries lastBuildId, the build that rendered its now-orphaned baseline). newNextCursor / changedNextCursor / removedNextCursor page the rest with list_pr_stories. No image URLs - fetch pixels by storyId with get_diff / render_diff_image. Requires the PR visual changeset feature.

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `prNumber` (integer): Resolve the latest build for this PR number.

Output parameters:

- `base` (string)
- `changed` (array)
- `changedNextCursor` (string|null)
- `counts` (object)
- `new` (array)
- `newNextCursor` (string|null)
- `removed` (array)
- `removedNextCursor` (string|null)

### `list_comments` (~174 tokens)

List the review comments on a build's diffs

Every review comment on a build's changed stories (resolved by commitSha/prNumber/buildId), each carrying its diffResultId, author (human name or 'agent'), body, createdAt, and anchor - where on the candidate image it points: null (whole diff), {type:'point',x,y}, {type:'rect',x,y,w,h}, or {type:'path',points,closed}, all normalized 0..1 to the candidate image. Use it to read what a designer/QA (or another agent) flagged on a screenshot before acting. Requires the image comments feature.

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `prNumber` (integer): Resolve the latest build for this PR number.

Output parameters:

- `comments` (array)

### `list_pr_stories` (~282 tokens)

Page through the PR-vs-base changeset by kind

Page through the PR-vs-base changeset stories of one kind (resolved by commitSha/prNumber/buildId) - use it to read past get_pr_changeset's first page. kind='new' returns stories the PR adds that the base branch has no baseline for; kind='changed' returns stories whose image differs from the base branch's accepted image (even if accepted mid-PR, with status=accepted); kind='removed' returns stories that HAD a baseline on the base branch but are gone from head (a deletion; each carries lastBuildId, not a review status or verdict). Returns { stories, nextCursor }: pass nextCursor back as `cursor` for the next page; null means no more. limit defaults to 25 (max 100). Requires the PR visual changeset feature.

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `cursor` (string): The nextCursor from a prior page; omit for the first page.
- `kind` (string, required): Which changeset stories to page: new (added), changed (vs base), or removed (deleted).
- `limit` (integer): Page size (default 25, max 100).
- `prNumber` (integer): Resolve the latest build for this PR number.

Output parameters:

- `nextCursor` (string|null)
- `stories` (array)

### `get_diff` (~281 tokens)

Get per-story diff detail with image URLs

Per-story diff detail for a build (resolved by commitSha/prNumber/buildId). Returns diff metrics and presigned, time-limited URLs (download them to a file, or link them in a PR comment) for the baseline, candidate, and diff PNGs. Defaults to the changed stories; pass storyId for one specific story. When that storyId is an UNCHANGED story it returns its baseline (diffResultId null, changed false, the baseline URL as both baselineUrl and candidateUrl) - the story rendered identical to baseline. Use render_diff_image instead when you want the actual pixels inline for a vision model, not a URL. When AI review is on, each diff carries the judge's call: aiVerdict (intended|regression), aiConfidence, aiSummary (what changed), aiReasoning, and aiFlagReason; all null when AI review didn't run for it. Each diff also carries comments {total, unresolved} for THAT story - unresolved>0 means an open review note; read the thread with list_comments before accepting.

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `prNumber` (integer): Resolve the latest build for this PR number.
- `storyId` (string): Limit to one story id.

Output parameters:

- `diffs` (array)

### `render_diff_image` (~542 tokens)

Fetch the actual pixels of a story image

Fetch a story's image as an INLINE image (base64 pixels, not a URL) so a vision model can look at it directly. Needs a native MCP client that renders image content; piped through raw curl it is useless (use get_diff's URLs there instead). Two ways to address it: (1) diffResultId + which for a CHANGED story - which is baseline|candidate|diff (the triptych) or before_after, the baseline and candidate SIDE BY SIDE (before on the left, after on the right) cropped to the changed region - and when a story changed in SEVERAL far-apart places, one such crop PER region stacked top to bottom, so a header-plus-footer change is two tight crops, not a page-tall image. before_after is usually what you want for a code change - it zooms to what moved instead of a full page. Get diffResultId from get_build (changedStories[].diffResultId) or get_diff. (2) a build selector (commitSha|prNumber|buildId) + storyId for ANY story's current image - the candidate if it changed this build, else its baseline. This second form is the only way to see an UNCHANGED/passed story's pixels (list them via list_build_stories status=unchanged), so you can confirm 'identical to baseline'. Errors if the image doesn't exist (a genuinely new story has no baseline, so no before_after either).

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `diffResultId` (string): A CHANGED story's diff result id (from get_build/get_diff); pair with `which`.
- `prNumber` (integer): Resolve the latest build for this PR number.
- `pxPagination` (object): Paginate a TALL image slice by slice instead of one unreadable image: return the `height` device px starting at y=`offset`, so a 5000px page is reviewed in readable slices. Omit for the whole image.…
- `storyId` (string): With a build selector: fetch THIS story's current image (works for unchanged stories).
- `which` (string): For the diffResultId form: baseline|candidate|diff (one triptych image, default candidate), or before_after (baseline+candidate side by side, cropped to the change - one crop per changed region, stac…

### `review_diff` (~194 tokens)

Accept, deny, or ignore one story's change

Record a review on a single diff result (get diffResultId from get_build/get_diff). 'accept' makes the candidate the new baseline for that story on its branch, so the next build is clean; 'deny' records the rejection without changing the baseline; 'ignore' excludes the story from the gate persistently (the snapshot keeps differing on future builds but no longer flags the check) — use it for an intentional, ongoing diff like an animation or a live timestamp. This is the same accept/deny/ignore as the dashboard, attributed to your project key. Use after you've inspected the diff (e.g. with render_diff_image) and decided intended vs. regression.

Input parameters:

- `decision` (string, required): 'accept' advances the baseline; 'deny' records a rejection; 'ignore' excludes the story from the gate.
- `diffResultId` (string, required): The diff result id from get_build or get_diff.

Output parameters:

- `decision` (string)
- `diffResultId` (string)

### `accept_build` (~169 tokens)

Accept every changed story in a build

Accept ALL changed stories in one build at once (resolved by commitSha/prNumber/buildId), advancing each story's per-branch baseline so the next build is clean. This is the bulk form of review_diff='accept' — use it when you've decided the whole build's changes are intended. It accepts every changed story, including stories that already have a prior denied review; failed stories are unaffected. Returns the build triage after accepting (first page of changed stories, each now showing decision='accepted'; page the rest with list_build_stories if changedNextCursor is set).

Input parameters:

- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `prNumber` (integer): Resolve the latest build for this PR number.

Output parameters:

- `aiReview`
- `autoAcceptChanges` (boolean)
- `branch` (string)
- `buildId` (string)
- `changedNextCursor` (string|null)
- `changedStories` (array)
- `comments` (object)
- `commitSha` (string)
- `counts` (object)
- `createdAt` (string)
- `failedNextCursor` (string|null)
- `failedStories` (array)
- `gateStatus` (string)
- `prNumber` (number|null)
- `status` (string)

### `post_comment` (~425 tokens)

Comment on a build's diff

Leave a review comment on one of a build's changed-story diffs (resolve the build by commitSha/prNumber/buildId, target the diff by diffResultId from get_build/get_diff). The comment is authored as the agent. Optionally anchor it to a spot on the candidate image with `anchor`: omit or null for a whole-diff comment, {type:'point',x,y} to pin a point, {type:'rect',x,y,w,h} for a box, or {type:'path',points:[{x,y},...],closed} for a shape - all coordinates 0..1 normalized to the candidate image. `side` picks the pane ('after' the candidate, default; 'before' the baseline). Pass `parentId` (a root comment id from list_comments) to REPLY in that thread instead - a reply inherits the root's side and carries no anchor, so `anchor`/`side` are ignored. A new root comment is refused when a newer build exists on the branch (comment on the latest build); replies stay allowed. Requires the image comments feature.

Input parameters:

- `anchor`: Where on the candidate image to pin it (0..1 normalized): omit/null = whole diff; {type:'point',x,y}; {type:'rect',x,y,w,h}; {type:'path',points,closed}. Ignored on a reply.
- `body` (string, required): The comment text.
- `buildId` (string): Resolve this exact build id.
- `commitSha` (string): Resolve the build for this git commit SHA.
- `diffResultId` (string, required): The diff result to comment on (from get_build/get_diff).
- `parentId` (string): Reply to this thread ROOT comment's id (from list_comments) instead of starting a new thread.
- `prNumber` (integer): Resolve the latest build for this PR number.
- `side` (string): Which pane: 'after' (candidate, default) or 'before' (baseline). Ignored on a reply.

Output parameters:

- `id` (string)

### `update_comment` (~72 tokens)

Edit a comment's text

Replace the body of a comment (get its id from list_comments). An agent key can edit only agent-authored comments, never a human's. Requires the image comments feature.

Input parameters:

- `body` (string, required): The new comment text.
- `commentId` (string, required): The comment id to edit (from list_comments).

Output parameters:

- `id` (string)

### `resolve_comment` (~94 tokens)

Resolve or reopen a comment thread

Mark a comment thread resolved or reopen it (get the id from list_comments). Resolving stamps the thread ROOT, so pass a root comment's id - a reply id is a no-op. Any team writer may toggle this. Requires the image comments feature.

Input parameters:

- `commentId` (string, required): The thread root comment id (from list_comments).
- `resolved` (boolean, required): true to resolve the thread, false to reopen it.

Output parameters:

- `id` (string)
- `resolved` (boolean)

### `delete_comment` (~69 tokens)

Delete a comment

Soft-delete a comment (get its id from list_comments). An agent key can delete only agent-authored comments, never a human's. Deleting a thread root removes its replies too. Requires the image comments feature.

Input parameters:

- `commentId` (string, required): The comment id to delete (from list_comments).

Output parameters:

- `deleted` (boolean)
- `id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/igrlk-uiverify/api-mcp#diagnostics

## Score history

- 2026-09-20: 72
- 2026-09-19: 71
- 2026-09-18: 71
- 2026-09-17: 70
- 2026-09-16: 70
- 2026-09-15: 69
- 2026-09-14: 69
- 2026-09-13: 68
- 2026-09-12: 68
- 2026-09-11: 67
- 2026-09-10: 67
- 2026-09-09: 66
- 2026-09-08: 66
- 2026-09-07: 65
- 2026-09-06: 65
- 2026-09-05: 36
- 2026-09-04: 36

## Common questions

### What is the UI Verify MCP server?

UI Verify is an MCP server listed in the public MCP registry as io.github.igrlk/uiverify. MCP server for visual regression testing: triage a PR's UI diffs from your coding agent. This page covers its hosted endpoint (https://uiverify.ai/api/mcp).

### Is the UI Verify MCP server safe to use?

UI Verify scores 72 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 UI Verify MCP server expose?

UI Verify exposes 14 tools: list_builds, get_build, list_build_stories, get_pr_changeset, list_comments, and 9 more. Their descriptions and schemas cost roughly 3,416 tokens of context every time the server is loaded.

### Does the UI Verify MCP server require authentication?

No. We connected to UI Verify without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the UI Verify MCP server still maintained?

UI Verify is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://uiverify.ai/api/mcp
- Authorisation metadata: https://uiverify.ai/.well-known/oauth-protected-resource/api/mcp
- Repository: https://github.com/uiverify/uiverify
- Website: https://uiverify.ai/
- Changelog RSS feed: https://verifymcp.io/servers/igrlk-uiverify/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/igrlk-uiverify/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/igrlk-uiverify/api-mcp