# Kadmo agent runtime (npm · @kadmo/cli)

Kadmo agent runtime on your computer: workflows, skill packs and Chrome automation for AI agents

- Trust score: 60/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@kadmo/cli`: 60/100 (this document), [markdown](https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli.md), [page](https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli)

## Channel facts

- Registry: `npm`
- Package: `@kadmo/cli`
- Version: `0.5.1`
- 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 2026-11-21.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects @fastify/static 9.3.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 49 of 172 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (UNLICENSED) isn't a recognized OSI-approved license.
  - Actively maintained (last published 8 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4435 tokens (~130/item across 34 items; 34 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 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.
  - All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 34 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 Kadmo agent runtime MCP server?

Kadmo agent runtime runs locally as an npm package, launched with npx -y @kadmo/cli mcp. 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 ai-kadmo-kadmo-agent -- npx -y @kadmo/cli mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-kadmo-kadmo-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@kadmo/cli",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-kadmo-kadmo-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@kadmo/cli",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-kadmo-kadmo-agent -- npx -y @kadmo/cli mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-kadmo-kadmo-agent --command npx --arg -y --arg @kadmo/cli --arg mcp
```

### Hermes

```yaml
mcp_servers:
  ai-kadmo-kadmo-agent:
    command: "npx"
    args: ["-y", "@kadmo/cli", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-kadmo-kadmo-agent": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@kadmo/cli",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-kadmo-kadmo-agent -t stdio -c npx -a -y @kadmo/cli mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-kadmo-kadmo-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@kadmo/cli",
        "mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-19 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 59, +3)

- [functional improvement] Stability: unverified → 0.17

### 2026-11-13 (score 56, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-12 (score 41)

First indexed and scored.

## MCP tools (34)

### `run_workflow` (~89 tokens)

Execute a workflow automation by ID. Returns a run_id for tracking execution status.

Input parameters:

- `params` (object): Key-value parameters required by the workflow
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `workflow_id` (string, required): Unique identifier of the workflow

### `get_run_log` (~35 tokens)

Retrieve the execution log for a completed workflow run.

Input parameters:

- `run_id` (string, required): The run ID returned from run_workflow

### `list_workflows` (~26 tokens)

List all available workflow automations.

Input parameters:

- `source` (string): Filter by source

### `get_workflow` (~30 tokens)

Get detailed information about a specific workflow.

Input parameters:

- `workflow_id` (string, required): Unique identifier of the workflow

### `list_run_logs` (~41 tokens)

List recent workflow execution logs.

Input parameters:

- `limit` (number): Maximum number of logs to return
- `workflow_id` (string): Filter logs by workflow ID

### `publish_artifact` (~374 tokens)

Publish a piece of evidence (a screenshot, a design mockup, an RCA/coverage report) to the portal RIGHT NOW, mid-session, and get back a paste-ready snippet to cite in your ONE resolution comment on the ticket. The file is uploaded, attached to the ticket automatically, and given a tokenized no-login download link — the snippet contains that link (a portal issue gets a markdown link to the file). A report attached to a ticket is numbered and named by the portal (<KEY>_<playbook>_<step>_<NN>), and its snippet leads with a "Report: #NN <link>" line to paste as it is. Use this the moment you have evidence worth showing, instead of waiting for the end of the session (nothing you save after your comment is written can be cited in it). Works on a dispatched job and for every turn of a live app editing session; on a ticketless/chat job it returns a download link only. Files must be ≤ 25 MB and live under your home directory. On any failure the file is left on disk and still uploads at session end, so save deliverables under artifacts/ as a fallback.

Input parameters:

- `caption` (string): Optional short label for the snippet. Shown only in the returned snippet as a hint for your comment; it is NOT stored on the artifact.
- `kind` (string): Gallery category. Optional — inferred from the file extension when omitted (images → screenshot, .svg/.html → mock, .pdf/.md/.txt/.csv/.json → report, .mp4/.webm → video).
- `path` (string, required): Path to the file to publish. A relative path resolves against your workspace (~/workspace); an absolute path is also accepted, as long as it stays within your home directory.

### `publish_report` (~322 tokens)

Hand your step report over to the portal as the LAST action of a dispatched job, instead of posting the ticket comment yourself. The portal records the verdict on the step (the playbook gate reads it from there), writes the ticket comment from your report in the account's report shape — a readable comment, a short summary with the report attached as a numbered file, both, or nothing at all on the quiet shape — translates it when a report language is set, and edits the comment of an earlier call in the same step instead of posting again. Publish evidence with publish_artifact first and pass its links as evidence. Every failure is non-fatal: the result then tells you to post your ONE comment yourself.

Input parameters:

- `body` (string, required): The full report in Markdown — the sections your workflow asks for (what changed, how to verify, the handoff checklist, the findings). No closing verdict line: the portal adds it.
- `evidence` (array): Links that evidence the report: the PR, the download links publish_artifact returned (at most 20).
- `filename` (string): Optional name for the report file (Markdown); the portal numbers it on the ticket when it attaches it.
- `summary` (string, required): One or two sentences: what the step did and where it stands (at most 2,000 characters).
- `verdict` (string, required): The step verdict token, one of the workflow's verdicts (e.g. PR_OPEN, WORK_CONTINUE, BLOCKED, PASS, FAIL). Only the token — never a sentence.

### `get_browser_status` (~44 tokens)

Check if the browser extension is connected, and list this session's window and tabs (protocol 2) or the one shared tab and who holds it (protocol 1).

### `capture_page` (~55 tokens)

Capture selectors and interactive elements from the current page.

Input parameters:

- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `navigate` (~65 tokens)

Navigate the connected browser tab to a URL.

Input parameters:

- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `url` (string, required): The URL to navigate to

### `snapshot` (~134 tokens)

Capture accessibility snapshot of the current page. Returns YAML with element refs for use with click/type. Use includeContent=true to also include visible text content as markdown. Note: taking a snapshot may dismiss inline modals or popups — use screenshot instead if you need to verify modal content.

Input parameters:

- `includeContent` (boolean): Include visible text content in the snapshot as markdown (default: false). Useful for reading articles, documentation, or any page content.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `click` (~104 tokens)

Click an element on the page.

Input parameters:

- `element` (string): Human-readable element description (for logging).
- `ref` (number): Element reference from snapshot (the number after ref=).
- `selector` (string): CSS selector for the element. Supports :has-text("text") pseudo-selector.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `type` (~111 tokens)

Type text into an input element.

Input parameters:

- `element` (string): Human-readable element description.
- `ref` (number): Element reference from snapshot.
- `selector` (string): CSS selector for the input element.
- `submit` (boolean): Press Enter after typing (default: false).
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `text` (string, required): Text to type.

### `press_key` (~171 tokens)

Press a key on the keyboard. Use this for keyboard shortcuts, Tab navigation, Enter, Escape, arrow keys, etc. Supports key combinations like "Ctrl+A" or "Shift+Tab".

Input parameters:

- `key` (string, required): Key to press. Examples: "Tab", "Enter", "Escape", "ArrowDown", "Backspace", "Shift+Tab", "Ctrl+A". For single characters, use the character directly (e.g., "a").
- `ref` (number): Optional element reference from snapshot to focus before pressing the key.
- `selector` (string): Optional CSS selector to focus before pressing the key.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `scroll` (~73 tokens)

Scroll the page.

Input parameters:

- `amount` (number): Scroll amount in pixels (default: 300).
- `direction` (string, required): Scroll direction.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `extract` (~63 tokens)

Extract text content from an element.

Input parameters:

- `selector` (string, required): CSS selector for the element.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `screenshot` (~275 tokens)

Capture a screenshot of the current page. Prefer cropping to a specific area instead of capturing the full viewport — use ref (from snapshot), selector (CSS), or region (manual rect) to save context tokens. Full viewport is fine for first visit to a new page; after that, crop to the relevant section. Pass path to write the PNG to a file instead of returning image bytes — that is what you want for docs screenshots and QA evidence, since the file can then be published with publish_artifact and never enters your context.

Input parameters:

- `path` (string): Write the PNG here instead of returning image bytes; returns the path and byte count as text. Accepts ~/... or an absolute path; a relative path resolves against ~/workspace. Must stay inside the hom…
- `ref` (number): Element reference from snapshot (the number after ref=). Crops screenshot to that element with padding.
- `region` (object): Manual crop region in CSS pixels (viewport coordinates).
- `selector` (string): CSS selector for the element. Crops screenshot to that element with padding.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `select_option` (~167 tokens)

Select an option from a native <select> dropdown element. Use this instead of click for <select> elements, as native dropdowns cannot be controlled via click events.

Input parameters:

- `element` (string): Human-readable element description (for logging).
- `label` (string): The visible text of the option to select (matches <option> text content).
- `ref` (number): Element reference from snapshot (the number after ref=).
- `selector` (string): CSS selector for the <select> element.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `value` (string): The option value to select (matches <option value="...">).

### `fill` (~123 tokens)

Fill a form field by setting its value programmatically. Unlike "type" (which simulates keystrokes), "fill" sets the value directly and triggers React/Vue/Angular change events. Use this for framework-controlled inputs where "type" doesn't work.

Input parameters:

- `selector` (string, required): CSS selector for the input element.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `value` (string, required): Value to set on the input.

### `wait` (~101 tokens)

Wait for an element to appear on the page. Blocks until the element matching the selector exists in the DOM, or throws after timeout.

Input parameters:

- `selector` (string, required): CSS selector to wait for.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `timeout` (number): Maximum wait time in milliseconds (default: 5000).

### `exists` (~99 tokens)

Check if an element exists on the page. Returns true/false without throwing. Useful for conditional logic.

Input parameters:

- `selector` (string, required): CSS selector to check.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `timeout` (number): How long to wait before returning false, in milliseconds (default: 2000).

### `extract_all` (~126 tokens)

Extract text from all elements matching a selector, joined by a separator. Useful for getting lists of items, table columns, or repeated elements.

Input parameters:

- `attribute` (string): Optional attribute to extract instead of text content (e.g., "href", "src").
- `selector` (string, required): CSS selector matching multiple elements.
- `separator` (string): String to join results with (default: "\n").
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `extract_map` (~130 tokens)

Extract structured data from repeated elements. For each element matching the outer selector, extracts named fields using sub-selectors. Returns JSON array of objects.

Input parameters:

- `fields` (object, required): Map of field names to extraction rules. Each rule has a "selector" (relative CSS selector) and optional "attribute".
- `selector` (string, required): CSS selector for the repeating container elements (e.g., "table tbody tr", ".card").
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `scroll_into_view` (~98 tokens)

Scroll a specific element into the viewport. More precise than "scroll" — targets an exact element.

Input parameters:

- `block` (string): Vertical alignment in viewport (default: "center").
- `selector` (string, required): CSS selector for the element to scroll into view.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `hover` (~67 tokens)

Hover over an element (positions cursor for scroll targeting).

Input parameters:

- `selector` (string, required): CSS selector for the element.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `inject_css` (~159 tokens)

Inject a CSS rule into the current page. The main use is pre-capture redaction: blur or hide sensitive elements, then screenshot to a file, so no unredacted image ever exists. Pass an id to make the injection replaceable — injecting the same id again swaps the rule rather than stacking a second one.

Input parameters:

- `css` (string, required): CSS to inject, e.g. ".user-email { filter: blur(6px); }"
- `id` (string): Optional identifier for the injected style element, so it can be replaced or removed later.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `evaluate` (~86 tokens)

Execute JavaScript in the browser page context and return the result. Useful for reading page state, checking values, or performing calculations.

Input parameters:

- `js` (string, required): JavaScript code to evaluate in the page context.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `browser_batch` (~664 tokens)

Run a SEQUENCE of browser actions in ONE call instead of one round trip per action. Each step is the same shape you would pass to the individual tool, plus a "cmd" field naming which tool to run.

A batch is a DETERMINISTIC run: actions you already know the selectors for, executed top to bottom, halting at the first failure (unless on_error:"continue"). By default it ends by returning a fresh accessibility snapshot of the resulting page, so you can decide the next move in the same turn. The moment you need to SEE something before choosing an action, end the batch and read the returned snapshot.

Guidance:
\- Prefer CSS selectors over refs inside a batch. Refs come from a prior snapshot and go stale the instant a step re-renders the page; selectors survive.
\- After a navigate (or an action that loads new content), add a { "cmd": "wait", "selector": "..." } step before interacting with the new content.
\- Add "optional": true to a step whose failure should not halt the batch.
\- Add "return": "drop" to a side-effect-only step you do not need echoed back (e.g. a screenshot taken only to trigger lazy-load).

Batchable cmds: navigate, wait, exists, click, type, fill, press_key, select_option, scroll, scroll_into_view, hover, extract, extract_all, extract_map, snapshot, screenshot, inject_css, evaluate.

To capture a redacted screenshot in one call: navigate → inject_css (blur the sensitive selectors) → wait → screenshot with a "path". The shot lands on disk already redacted and no image bytes come back.

Example — log in then land on the dashboard in one call:
{ "steps": [ { "cmd": "navigate", "url": "https://app.example.com/login" }, { "cmd": "wait", "selector": "#user" }, { "cmd": "fill", "selector": "#user", "value": "alice" }, { "cmd": "fill", "selector": "#pw", "value": "secret" }, { "cmd": "click", "selector": "button[type=submit]" }, { "cmd": "wait", "selector": ".dashboard" } ] }

Input parameters:

- `on_error` (string): "stop" (default): halt at the first failed step, marking the rest skipped. "continue": run every step regardless.
- `snapshot_tail` (boolean): Append a fresh accessibility snapshot of the final page to the response so you can decide the next action (default: true). Skipped automatically when the last step is already a snapshot or screenshot…
- `steps` (array, required): Ordered list of actions. Each item is { "cmd": "<tool name>", ...that tool's arguments }. Optional per-step keys: "optional" (boolean — failure never halts the batch) and "return": "drop" (omit this…
- `tab` (string): The tab every step drives (a handle such as "t2" from list_tabs or new_tab); a step may name its own "tab". Default: this session's current tab.

### `set_basic_auth` (~190 tokens)

Provide HTTP Basic Auth credentials so the browser logs in silently instead of showing the native username/password modal, which would otherwise block the page and hang automation. Applies to the connected tab. Omit "origin" to use the credentials for any site that challenges; pass "origin" (e.g. "https://staging.example.com") to scope them to one site. When a challenge has no matching credentials it is dismissed so the page never hangs.

Input parameters:

- `origin` (string): Optional origin to scope the credentials to (e.g. "https://staging.example.com"). Omit to apply to any challenged site.
- `password` (string, required): Basic Auth password.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.
- `username` (string, required): Basic Auth username.

### `clear_basic_auth` (~104 tokens)

Remove stored HTTP Basic Auth credentials. Omit "origin" to clear all stored credentials; pass "origin" to clear just that site.

Input parameters:

- `origin` (string): Optional origin to clear (e.g. "https://staging.example.com"). Omit to clear all stored credentials.
- `tab` (string): The tab to drive: a handle of this session such as "t2" (list_tabs, new_tab). Default: the session's current tab.

### `list_tabs` (~65 tokens)

List the tabs of THIS session's browser window: each tab's handle ("t1", "t2", …), URL and title, which one is current (the one a call without "tab" drives), and which the person lent. Other sessions' tabs are never listed.

### `new_tab` (~103 tokens)

Open a new tab in THIS session's browser window and return its handle. Pass that handle as "tab" on every call that should drive it; calls without "tab" keep driving the current tab. A sub-agent opens its own tab this way so two agents never share a page.

Input parameters:

- `active` (boolean): Bring the tab to the front of the window (default: true).
- `url` (string): The page to open (default: a blank tab).

### `close_tab` (~55 tokens)

Close a tab of THIS session by its handle. A tab the person lent to the session goes back to them instead of closing.

Input parameters:

- `tab` (string, required): The handle of the tab to close (e.g. "t2").

### `select_profile` (~86 tokens)

List the Chrome profiles connected to the runtime (one Kadmo extension per profile), or move THIS session to one of them. Moving closes the session's window in the old profile; the next browser call opens it in the new one.

Input parameters:

- `profile` (string): The profile's label (e.g. "Chrome · a9f3") or install id; omit to list them.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli#diagnostics

## Score history

- 2026-11-21: 60
- 2026-11-20: 60
- 2026-11-19: 60
- 2026-11-18: 59
- 2026-11-17: 59
- 2026-11-16: 56
- 2026-11-15: 56
- 2026-11-14: 56
- 2026-11-13: 56
- 2026-11-12: 41

## Common questions

### What is the Kadmo agent runtime MCP server?

Kadmo agent runtime is an MCP server listed in the public MCP registry as ai.kadmo/kadmo-agent. Kadmo agent runtime on your computer: workflows, skill packs and Chrome automation for AI agents. This page covers its npm package (@kadmo/cli).

### Is the Kadmo agent runtime MCP server safe to use?

Kadmo agent runtime scores 60 out of 100 on VerifyMCP. We recorded 12 known advisories against it as of 21 November 2026. It declares no install or post-install scripts. 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 Kadmo agent runtime MCP server expose?

Kadmo agent runtime exposes 34 tools: run_workflow, get_run_log, list_workflows, get_workflow, list_run_logs, and 29 more. Their descriptions and schemas cost roughly 4,435 tokens of context every time the server is loaded.

### Is the Kadmo agent runtime MCP server still maintained?

Kadmo agent runtime is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Kadmo agent runtime MCP server under?

Kadmo agent runtime declares the UNLICENSED licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

### What did VerifyMCP test on the Kadmo agent runtime MCP server?

VerifyMCP ran 15 checks on Kadmo agent runtime, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Kadmo agent runtime: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@kadmo/cli
- Socket report: https://socket.dev/npm/package/@kadmo/cli
- Website: https://kadmo.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli.json
- HTML version of this page: https://verifymcp.io/servers/ai-kadmo-kadmo-agent/kadmo-cli
