# Capxule (remote · capxule.ai)

The context marketplace: expert guided journeys your assistant runs step by step.

- Trust score: 63/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `capxule.ai`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ai-capxule-capxule/capxule.md), [page](https://verifymcp.io/servers/ai-capxule-capxule/capxule)

## Channel facts

- Endpoint: `https://capxule.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2026.10.13`

## 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 2026-11-05.

- **Endpoint Security**: 57/100
  - 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 (restart_journey).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 69/100
  - 67% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1590 tokens (~144/item across 11 items; 9 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 22 days we've observed: 10 tool removals, 0 breaking changes, 0 auth/transport breaks, 7 additions.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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.
  - Supports UI / widget rendering.

## Install

### How do I install the Capxule MCP server?

Capxule is a hosted endpoint at https://capxule.ai/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 ai-capxule-capxule 'https://capxule.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-capxule-capxule": {
      "url": "https://capxule.ai/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.ai-capxule-capxule]
url = "https://capxule.ai/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  ai-capxule-capxule:
    url: "https://capxule.ai/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "ai-capxule-capxule": {
      "type": "http",
      "url": "https://capxule.ai/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.

### 2026-11-05 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-04 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-03 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-02 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-01 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-31 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-30 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-29 (score 63, −5)

- [security regression] Stability: 0.47 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security regression] Tool “account_bind” was removed
- [security regression] Tool “account_status” was removed
- [security regression] Tool “account_verify” was removed
- [security regression] Tool “browse_catalog” was removed
- [security regression] Tool “find_capsule” was removed
- [security regression] Tool “handoff” was removed
- [security regression] Tool “journey_state” was removed
- [security regression] Tool “list_categories” was removed
- [security regression] Tool “make_artifact” was removed
- [security regression] Tool “turn” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “open_journey” rewrote its description, which is the text the model reads
- [security] Tool “restart_journey” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 340 → 144
- [functional improvement] Tool coverage: 86% → 91%
- [functional] Schema quality: excellent → good
- [functional] Destructive annotations: 100 → pass
- [functional] New tool “browse_journeys”
- [functional] New tool “create_takeaway”
- [functional] New tool “find_journey”
- [functional] New tool “get_journey_progress”
- [functional] New tool “get_resume_link”
- [functional] New tool “list_journey_categories”
- [functional] New tool “take_journey_step”
- [cosmetic] “open_journey” reworded the description of “capsule_id”
- [cosmetic] “open_journey” reworded the description of “goal”
- [cosmetic] “open_journey” reworded the description of “resume”
- [cosmetic] Tool “open_journey” changed its title: Open or resume a journey → Open a journey
- [cosmetic] Tool “restart_journey” changed its title: Start a journey over → Restart a journey

## MCP tools (9)

### `find_journey` (~169 tokens)

Find a guided journey

Use when the user wants a guided, step-by-step journey on a topic, a skill or an exam. Searches the published journeys and returns up to three cards (id, title, summary, shape, languages, number of stops, estimated minutes, who it is for and not for, a premium flag, page_url). `in_progress: true` marks a journey this user already has open. When nothing matches, `alternatives` holds the three nearest journeys.

Input parameters:

- `limit` (integer): Max results, 1 to 3 (default 3).
- `locale` (string): The user's locale (en, fr, es, ar).
- `query` (string, required): The topic, skill or exam to search for, in a few words. The topic only, no personal details.

### `list_journey_categories` (~43 tokens)

List journey categories

Use when the user asks what kinds of journeys are available. Returns each category slug, a readable label, the number of journeys in it and a few example titles.

### `browse_journeys` (~116 tokens)

Browse journeys

Use when the user wants to look through the journeys, optionally within one category (a slug from list_journey_categories). Returns a page of the same cards as find_journey, with the total and next_offset.

Input parameters:

- `category` (string): A category slug from list_journey_categories (e.g. education). Omit for every category.
- `limit` (integer): Cards per page, 1 to 25 (default 10).
- `offset` (integer): Start position; pass next_offset from the previous page.

### `open_journey` (~179 tokens)

Open a journey

Use when the user chooses a journey to start or continue. Opens it, or resumes the user's session for it, and returns the session contract: `session`, the stop titles, the capabilities, the limits in turns and the first step. Calling it again for the same journey resumes the same session; it never resets progress.

Input parameters:

- `capsule_id` (string): The journey id from find_journey (uuid or short id). `welcome` opens the sandbox tour.
- `goal` (string): What the user wants from the journey, in a few words, if they said. No personal details.
- `locale` (string): Preferred locale; the beat echoes the locale actually served.
- `resume` (string): A resume code from get_resume_link.
- `slug` (string): The journey slug, when you hold that instead of the id.

### `take_journey_step` (~190 tokens)

Take a journey step

Use for every step after open_journey. Sends the user's choice and returns the next step: `answer`, `statement`, numbered `options` with ids, `media`, `progress` and `limits`. Send `pick` with an option id when the user chose an option or its number; otherwise send `say` with what the user said. `go` jumps to a stop from the contract; `drill` and `simulate` start practice on exam journeys; `exit` leaves practice. Supply a fresh `turn_id` per step; a repeat returns the stored step. If the step carries `wall`, tell the user `wall.for_human`.

Input parameters:

- `action` (required)
- `session` (string, required): The session handle from open_journey (starts with cxs_).
- `turn_id` (string): Your idempotency id for this step (fresh per step).

### `get_journey_progress` (~75 tokens)

Get journey progress

Use when the user asks where they are in a journey, how far they have come or how much is left. Returns the current stop, visited and remaining stops, percent done, practice stats, limits and a resume line.

Input parameters:

- `session` (string, required): The session handle from open_journey (starts with cxs_).

### `create_takeaway` (~98 tokens)

Create a takeaway

Use when the user asks for a summary to keep. Composes a markdown takeaway from this journey session: what the user asked, the key points and the stops visited. Available on connected accounts; otherwise returns not_available.

Input parameters:

- `kind` (string, required)
- `session` (string, required): The session handle from open_journey (starts with cxs_).
- `template_id` (string): Required for kind template: an id from capabilities.templates.

### `get_resume_link` (~61 tokens)

Get a resume link

Use when the user wants to continue the journey later, on the website or in another assistant. Returns a resume link and a short resume code for this session.

Input parameters:

- `session` (string, required): The session handle from open_journey (starts with cxs_).

### `restart_journey` (~98 tokens)

Restart a journey

Use only when the user explicitly asks to start a journey over, after confirming with them. Returns to the first step and clears the visited stops; turns already used stay used. Returns the same session contract as open_journey.

Input parameters:

- `capsule_id` (string): The journey id (uuid or short id).
- `locale` (string): Preferred locale.
- `slug` (string): The journey slug, when you hold that instead of the id.

## Diagnostics

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

## Score history

- 2026-11-05: 63
- 2026-11-04: 63
- 2026-11-03: 63
- 2026-11-02: 63
- 2026-11-01: 63
- 2026-10-31: 63
- 2026-10-30: 63
- 2026-10-29: 63
- 2026-10-28: 68
- 2026-10-27: 67
- 2026-10-26: 67
- 2026-10-25: 67
- 2026-10-24: 66
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 64
- 2026-10-19: 64
- 2026-10-18: 63
- 2026-10-17: 63
- 2026-10-16: 62
- 2026-10-15: 62
- 2026-10-14: 61

## Common questions

### What is the Capxule MCP server?

Capxule is an MCP server listed in the public MCP registry as ai.capxule/capxule. The context marketplace: expert guided journeys your assistant runs step by step. This page covers its hosted endpoint (https://capxule.ai/mcp).

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

Capxule scores 63 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 Capxule MCP server expose?

Capxule exposes 9 tools: find_journey, list_journey_categories, browse_journeys, open_journey, take_journey_step, and 4 more. Their descriptions and schemas cost roughly 1,029 tokens of context every time the server is loaded.

### Does the Capxule MCP server require authentication?

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

### Is the Capxule MCP server still maintained?

Capxule is still listed as active in the MCP registry. We last reached this channel on 5 November 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://capxule.ai/mcp
- Repository: https://github.com/Capxule/capxule-ai
- Website: https://capxule.com/connect
- Changelog RSS feed: https://verifymcp.io/servers/ai-capxule-capxule/capxule.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-capxule-capxule/capxule.json
- HTML version of this page: https://verifymcp.io/servers/ai-capxule-capxule/capxule