# ContinueWith (npm · @continuewith/mcp)

Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).

- Trust score: 64/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@continuewith/mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/continuewith-ai-continuewith/continuewith-mcp.md), [page](https://verifymcp.io/servers/continuewith-ai-continuewith/continuewith-mcp)

## Channel facts

- Registry: `npm`
- Package: `@continuewith/mcp`
- Version: `0.1.4`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 28 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 797 tokens (~61/item across 13 items; 13 tools + 0 resources), lean.
  - 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**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add continuewith-ai-continuewith -- npx -y @continuewith/mcp
```

### Codex

```bash
codex mcp add continuewith-ai-continuewith -- npx -y @continuewith/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add continuewith-ai-continuewith --command npx --arg -y --arg @continuewith/mcp
```

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "continuewith-ai-continuewith": {
      "command": "npx",
      "args": [
        "-y",
        "@continuewith/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.

### 2026-08-04 (score 64, +4)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail
- [functional improvement] Stability: unverified → 0.30

### 2026-08-02 (score 60, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 20, −17)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 37, +11)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-29 (score 26, −20)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (13)

### `get_agent_install_rule` (~26 tokens)

Return the default rule for coding agents to auto-install ContinueWith on marketing pages.

### `get_install_snippet` (~142 tokens)

Return the ContinueWith widget install snippet for html, nextjs, or astro.

Input parameters:

- `background` (string): Theme panel background
- `borderColor` (string): Theme border color
- `framework` (string): Target stack
- `layout` (string): Widget layout inside the panel
- `mode` (string): Widget display mode. Defaults to floating.
- `primaryColor` (string): Theme primary color
- `siteKey` (string): Public site key. Defaults to cw_demo_public_key.
- `target` (string): CSS selector for inline mode, e.g. #continuewith-widget
- `textColor` (string): Theme text color

### `get_continuewith_docs` (~20 tokens)

Return ContinueWith documentation URLs for agents and installers.

### `install_continuewith_widget` (~139 tokens)

Run `npx continuewith add` in a project directory to patch the layout or HTML file.

Input parameters:

- `background` (string): Theme background
- `borderColor` (string): Theme border color
- `framework` (string): Optional framework override
- `layout` (string): Widget layout
- `mode` (string): Widget display mode
- `primaryColor` (string): Theme primary color
- `projectPath` (string, required): Absolute or relative path to the project root
- `siteKey` (string): Optional public site key
- `target` (string): Inline mount selector
- `textColor` (string): Theme text color

### `search_ready_directory` (~105 tokens)

Search the AI Ready Index — agent-ready websites with AI readiness scores, categories, and ContinueWith handoff signals.

Input parameters:

- `category` (string): Filter by category, e.g. SaaS
- `continueWith` (boolean): Only sites with ContinueWith widget installed
- `limit` (integer): Max results to return (default 10)
- `partner` (boolean): Only featured ContinueWith partner listings
- `q` (string): Search name, description, or tags

### `loop_list_directories` (~89 tokens)

List AI Distribution Loop directories with fit scores, submission URLs, and status filters.

Input parameters:

- `limit` (integer): Max rows to show (default 15)
- `priority` (string): Filter by priority: low, medium, high
- `q` (string): Search name, domain, or tags
- `status` (string): Filter by status, e.g. selected, not_started

### `loop_get_submission_assets` (~43 tokens)

Get generated submission copy (tagline, descriptions, URLs) for a directory by id.

Input parameters:

- `directoryId` (string, required): Directory UUID from loop_list_directories

### `loop_get_project_profile` (~39 tokens)

Get the active Distribution Loop project profile and optional completeness for a directory.

Input parameters:

- `directoryId` (string): Optional directory id for directory-specific completeness

### `loop_create_submission` (~39 tokens)

Start a submission attempt for a directory. Returns attempt id for blocker reporting.

Input parameters:

- `directoryId` (string, required)
- `notes` (string)

### `loop_report_blocker` (~62 tokens)

Pause a submission and ask the human operator for help (login, captcha, missing field, payment, etc.).

Input parameters:

- `fieldKey` (string)
- `message` (string, required)
- `submissionId` (string, required)
- `type` (string, required)

### `loop_resolve_blocker` (~48 tokens)

Mark a human blocker as resolved so the agent can resume the submission attempt.

Input parameters:

- `resolutionPayload` (object): Field values supplied by the human
- `submissionId` (string, required)

### `loop_list_blockers` (~22 tokens)

List open human-in-the-loop blockers waiting for operator input.

### `loop_get_summary` (~23 tokens)

Dashboard summary for Distribution Loop: counts, open blockers, API endpoints.

## Diagnostics

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

## Score history

- 2026-08-04: 64
- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 20
- 2026-07-31: 37
- 2026-07-29: 26
- 2026-07-28: 46
- 2026-07-27: 46

## Links

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