# Atris (npm · atris)

Run Atris campaigns from any agent, and extract, check, or search brand design systems.

- Trust score: 55/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- npm · `atris`: 55/100 (this document), [markdown](https://verifymcp.io/servers/atrislabs-atris/atris.md), [page](https://verifymcp.io/servers/atrislabs-atris/atris)

## Channel facts

- Registry: `npm`
- Package: `atris`
- Version: `3.74.9`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-24.

- **Supply Chain Security**: 13/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: the version this server declares is not published in its registry.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: the version this server declares is not published in its registry.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to atrislabs/atris).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1110 tokens (~111/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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 Atris MCP server?

Atris runs locally as an npm package, launched with npx -y atris. 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 atrislabs-atris -- npx -y atris
```

### Cursor

```json
{
  "mcpServers": {
    "atrislabs-atris": {
      "command": "npx",
      "args": [
        "-y",
        "atris"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "atrislabs-atris": {
      "command": "npx",
      "args": [
        "-y",
        "atris"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add atrislabs-atris -- npx -y atris
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "atrislabs-atris": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "atris"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add atrislabs-atris --command npx --arg -y --arg atris
```

### Hermes

```yaml
mcp_servers:
  atrislabs-atris:
    command: "npx"
    args: ["-y", "atris"]
```

### Netclaw

```json
{
  "McpServers": {
    "atrislabs-atris": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "atris"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add atrislabs-atris -t stdio -c npx -a -y atris
```

### Other

```json
{
  "mcpServers": {
    "atrislabs-atris": {
      "command": "npx",
      "args": [
        "-y",
        "atris"
      ]
    }
  }
}
```

## 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.

### 2026-10-24 (score 55, +1)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → pass
- [functional] Package version: 3.74.6 → 3.74.9
- [functional] Package version: 3.74.6 → 3.74.8
- [functional] Package version: 3.74.6 → 3.74.7

### 2026-10-23 (score 54)

First indexed and scored.

## MCP tools (10)

### `design_extract` (~56 tokens)

extract a site's design system (colors, typography, layout, voice) as json. costs 10 credits, 2 on a cache hit.

Input parameters:

- `url` (string, required): site url to extract, e.g. https://stripe.com

### `design_check` (~47 tokens)

score how closely a page follows a reference brand. costs 20 credits.

Input parameters:

- `reference_url` (string, required): brand url to check against
- `source_url` (string, required): page being checked

### `design_search` (~49 tokens)

search brands already extracted by atris design. costs 1 credit.

Input parameters:

- `limit` (number): max results
- `query` (string, required): plain words, e.g. "dark developer tools brand"

### `campaign_list` (~74 tokens)

list every atris campaign with its state, money spent, and the next move. a campaign is a long goal with a judge (a command that exits 0 when the goal is met), a budget, and members.

Input parameters:

- `cwd` (string): workspace folder to run in; defaults to the folder this server started in

### `campaign_show` (~76 tokens)

show one campaign: judge and its last reading, budget, seats, missions, open asks, and the next move.

Input parameters:

- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `id` (string, required): campaign id, e.g. cmp-ship-billing-1a2b

### `campaign_new` (~137 tokens)

the easiest start: give a goal in plain words. the owner's engine drafts a judge script, atris runs it to prove it fails today, and returns the draft. start: true also starts the campaign. budget defaults to $20.

Input parameters:

- `budget` (number): dollars the campaign may spend (default 20)
- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `goal` (string, required): the goal in plain words
- `owner` (string): member who owns it (default mission-lead)
- `start` (boolean): start the campaign once the drafted judge fails today

### `campaign_start` (~212 tokens)

start a campaign with a judge you wrote. the judge runs first and a judge that already passes is refused: it must fail today. print graded output like "ℹ pass 3" and "ℹ fail 2" so progress shows.

Input parameters:

- `as` (string): the member you are working as, e.g. builder; writes are never recorded as a person
- `bet` (string): what you think will work
- `budget` (number, required): dollars the campaign may spend
- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `id` (string): optional id, cmp-<lowercase-words>
- `judge` (string, required): shell command that exits 0 only when the goal is met
- `owner` (string): member who owns it (default mission-lead)
- `seats` (array): members who work on it, as member or member:role
- `title` (string, required): short name for the goal

### `campaign_run` (~168 tokens)

let the campaign run itself for at most max_steps steps: it judges, proposes missions, and runs them. it stops early when the judge passes, the money runs out, or a person must answer an ask. returns the stop reason.

Input parameters:

- `as` (string): the member you are working as, e.g. builder; writes are never recorded as a person
- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `id` (string, required): campaign id, e.g. cmp-ship-billing-1a2b
- `max_steps` (number): steps before it stops, 1 to 20 (default 3)
- `parallel` (number): missions at once, 1 to 5 (default 3)

### `campaign_ask` (~136 tokens)

stop for a person before anything that cannot be undone: sending, paying, deleting, deploying, publishing. the campaign waits until a person answers.

Input parameters:

- `as` (string): the member you are working as, e.g. builder; writes are never recorded as a person
- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `id` (string, required): campaign id, e.g. cmp-ship-billing-1a2b
- `mission` (string): mission id the ask belongs to
- `question` (string, required): the question, with what happens on yes

### `campaign_answer` (~155 tokens)

pass along a person's answer to an open ask. an agent cannot close an ask: the answer is recorded and the ask stays open until the person runs the returned person_command in their own terminal.

Input parameters:

- `answer` (string, required): the person's answer in their words
- `as` (string): the member you are working as, e.g. builder; writes are never recorded as a person
- `ask_id` (string, required): ask id from campaign_show, e.g. a-1b2c3d
- `cwd` (string): workspace folder to run in; defaults to the folder this server started in
- `id` (string, required): campaign id, e.g. cmp-ship-billing-1a2b

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/atrislabs-atris/atris#diagnostics

## Score history

- 2026-10-24: 55
- 2026-10-23: 54

## Common questions

### What is the Atris MCP server?

Atris is an MCP server listed in the public MCP registry as io.github.atrislabs/atris. Run Atris campaigns from any agent, and extract, check, or search brand design systems. This page covers its npm package (atris).

### Is the Atris MCP server safe to use?

Atris scores 55 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Atris MCP server expose?

Atris exposes 10 tools: design_extract, design_check, design_search, campaign_list, campaign_show, and 5 more. Their descriptions and schemas cost roughly 1,110 tokens of context every time the server is loaded.

### Is the Atris MCP server still maintained?

Atris is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Atris MCP server under?

Atris declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/atris
- Socket report: https://socket.dev/npm/package/atris
- Repository: https://github.com/atrislabs/atris
- Website: https://atris.ai/
- Changelog RSS feed: https://verifymcp.io/servers/atrislabs-atris/atris.xml
- Changelog JSON feed: https://verifymcp.io/servers/atrislabs-atris/atris.json
- HTML version of this page: https://verifymcp.io/servers/atrislabs-atris/atris