# Verdict

> Verdict is a freemium MCP server for design and media. Six design-review tools that critique screens, copy, journeys and briefs for agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $5 a month
- **Platforms:** API, Web
- **Website:** https://verdict.allthepossibles.com
- **MCP Registry name:** com.allthepossibles/verdict
- **Categories:** design and media
- **Listing updated:** 2026-11-15

## About

Unlike a checker with fixed rules, Verdict sends your material to a review model and returns findings with an honest confidence marker. Critique results are marked critical, warning or note, each tagged as observed or inferred, with the smallest fix and a ship-or-not summary. The decision stays with you.

The six tools aim at distinct failures: finding forgotten states of a feature, mapping the entries, exits and interruptions around a goal, auditing interface strings, pulling unchecked assumptions out of a brief as research questions, and spotting one concept that goes by several names across UI, docs and API. The copy audit leaves strings that already work untouched.

The free demo allows 2 calls a day with no key, and the text goes to the review model and is not stored. Sending your own Anthropic key in an x-anthropic-key header removes that limit, because the call runs on your account. Basic is $5 a month and Pro $19 a month with a larger allowance.

## Features

- **Ranked critique:** Rates design problems critical, warning or note with evidence and a smallest fix.
- **State matrix:** Lists every state a feature can be in, including undrawn ones, and likely gaps.
- **Journey mapping:** Names forgotten entries, exits and interruptions around a goal.
- **Copy audit:** Rewrites failing buttons, errors and notifications and leaves good strings alone.
- **Assumption finder:** Turns a brief's unchecked beliefs into research questions ranked by risk.
- **Terminology check:** Clusters terms that name the same concept differently across sources.

## Good for

- Review a screen before handing it to engineering
- Find missing empty and error states
- Test a product brief for hidden assumptions
- Tidy inconsistent UI terminology
- Run a review step in an agent loop or CI job

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http verdict https://verdict.allthepossibles.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://verdict.allthepossibles.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "verdict": {
      "url": "https://verdict.allthepossibles.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.allthepossibles.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "verdict": {
      "serverUrl": "https://verdict.allthepossibles.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "verdict": {
      "type": "http",
      "url": "https://verdict.allthepossibles.com/mcp"
    }
  }
}
```

## Tools

- `critique_experience`: Finds and ranks problems in a design with evidence and fixes.
- `generate_state_matrix`: Lists every state a feature can be in and likely gaps.
- `map_journey`: Maps stages around a goal and the forgotten entries, exits and interruptions.
- `audit_copy`: Reviews and rewrites interface strings.
- `find_assumptions`: Extracts assumptions from a brief and pairs each with a research question.
- `check_terminology`: Finds one concept named several ways across UI, docs and API.

## FAQ

### Is there a free option?

Yes, all six tools with 2 calls a day per caller and no key.

### How do I lift the free limit?

Send your own Anthropic key in an x-anthropic-key header, or pay for Basic or Pro.

### Is my text stored?

The site says it goes to the review model and is not stored.

### Does it call the tools over REST?

Yes, there is one route per tool, such as /api/audit_copy.

### Is Verdict free?

Verdict has a free plan, with paid plans for more usage or features. Paid plans start at $5 a month.

### How do I add Verdict to Claude Code?

Run this command in your terminal: claude mcp add --transport http verdict https://verdict.allthepossibles.com/mcp

### What are the best alternatives to Verdict?

The closest alternatives to Verdict are HyperFrames by HeyGen, ffmpeg-skill, AvatarSay — Fictional Character & Talking Video MCP, ChartAnt and VfxSmith.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [Hourlore](https://ai-powered.com/mcp/hourlore): Hourlore is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/verdict
