# Dedox (remote · api.dedox.ai)

Gives AI assistants read access to your Dedox help centre and knowledge base articles.

- Trust score: 77/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- remote · `api.dedox.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-dedox-dedox/api.md), [page](https://verifymcp.io/servers/ai-dedox-dedox/api)

## Channel facts

- Endpoint: `https://api.dedox.ai/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## 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 2026-11-06.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1293 tokens (~53/item across 24 items; 24 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

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

Dedox is a hosted endpoint at https://api.dedox.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-dedox-dedox 'https://api.dedox.ai/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

### 2026-11-06 (score 77, 0)

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

### 2026-11-05 (score 77, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-04 (score 77, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-03 (score 76, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-02 (score 76, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-01 (score 75, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-31 (score 75, +4)

- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: All 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-30 (score 71)

First indexed and scored.

## MCP tools (24)

### `list_articles` (~97 tokens)

List articles

List articles for a knowledge base with optional filters

Input parameters:

- `category` (string): Filter by category
- `knowledgeBaseId` (string, required): Knowledge base ID
- `limit` (number): Maximum number of results (1-100, default: 50)
- `offset` (number): Number of results to skip (default: 0)
- `status` (string): Filter by status
- `tags` (array): Filter by tags

### `get_article` (~26 tokens)

Get article

Get detailed information about a specific article

Input parameters:

- `articleId` (string, required): Article ID

### `create_article` (~161 tokens)

Create article

Create a new article in a knowledge base

Input parameters:

- `category` (string): Article category
- `content` (string, required): Article content (Markdown format, will be converted to HTML)
- `excerpt` (string): Short description or excerpt (max 500 characters)
- `knowledgeBaseId` (string, required): Knowledge base ID
- `seo` (object): SEO metadata object with optional fields: metaTitle (max 60 chars), metaDescription (max 160 chars), keywords (array of strings or comma-separated string)
- `slug` (string): URL slug (auto-generated from title if not provided)
- `status` (string): Article status (default: draft)
- `tags` (array): Array of tag strings
- `title` (string, required): Article title

### `update_article` (~182 tokens)

Update article

Update an existing article. Creates a new version with a change note.

Input parameters:

- `articleId` (string, required): Article ID
- `category` (string): Article category
- `changeNote` (string): Optional note describing the changes made (max 500 characters). If not provided, a summary of changed fields will be generated.
- `content` (string): Article content (Markdown format, will be converted to HTML)
- `excerpt` (string): Article excerpt (max 500 characters)
- `seo` (object): SEO metadata object with optional fields: metaTitle (max 60 chars), metaDescription (max 160 chars), keywords (array of strings or comma-separated string)
- `slug` (string): URL slug
- `status` (string): Article status
- `tags` (array): Array of tag strings
- `title` (string): Article title

### `delete_article` (~25 tokens)

Delete article

Delete an article (soft delete)

Input parameters:

- `articleId` (string, required): Article ID

### `list_knowledge_bases` (~20 tokens)

List knowledge bases

List all knowledge bases owned by the user

### `get_knowledge_base` (~31 tokens)

Get knowledge base

Get detailed information about a specific knowledge base

Input parameters:

- `knowledgeBaseId` (string, required): Knowledge base ID

### `create_knowledge_base` (~62 tokens)

Create knowledge base

Create a new knowledge base

Input parameters:

- `branding` (object): Branding configuration
- `name` (string, required): Knowledge base name
- `settings` (object): Knowledge base settings
- `subdomain` (string): Custom subdomain (auto-generated if not provided)

### `update_knowledge_base` (~68 tokens)

Update knowledge base

Update an existing knowledge base

Input parameters:

- `branding` (object): Branding configuration
- `knowledgeBaseId` (string, required): Knowledge base ID
- `name` (string): Knowledge base name
- `settings` (object): Knowledge base settings
- `subdomain` (string): Custom subdomain

### `delete_knowledge_base` (~30 tokens)

Delete knowledge base

Delete a knowledge base (soft delete)

Input parameters:

- `knowledgeBaseId` (string, required): Knowledge base ID

### `get_knowledge_base_analytics` (~58 tokens)

Get knowledge base analytics

Get analytics data for a knowledge base

Input parameters:

- `endDate` (string, required): End date (ISO format)
- `knowledgeBaseId` (string, required): Knowledge base ID
- `startDate` (string, required): Start date (ISO format)

### `get_article_analytics` (~53 tokens)

Get article analytics

Get analytics data for an article

Input parameters:

- `articleId` (string, required): Article ID
- `endDate` (string, required): End date (ISO format)
- `startDate` (string, required): Start date (ISO format)

### `search_articles` (~75 tokens)

Search articles

Search articles using full-text search

Input parameters:

- `knowledgeBaseId` (string): Filter by knowledge base ID
- `limit` (number): Maximum number of results (1-100, default: 50)
- `offset` (number): Number of results to skip (default: 0)
- `query` (string, required): Search query

### `get_article_categories` (~30 tokens)

List categories

Get all categories used in a knowledge base

Input parameters:

- `knowledgeBaseId` (string, required): Knowledge base ID

### `get_article_tags` (~30 tokens)

List tags

Get all tags used in a knowledge base

Input parameters:

- `knowledgeBaseId` (string, required): Knowledge base ID

### `create_category` (~51 tokens)

Create category

Create a new category in a knowledge base. It is listed straight away, including before an article uses it.

Input parameters:

- `knowledgeBaseId` (string, required): Knowledge base ID
- `name` (string, required): Category name

### `update_category` (~57 tokens)

Rename category

Rename a category in a knowledge base (updates all articles with that category)

Input parameters:

- `categoryName` (string, required): Current category name
- `knowledgeBaseId` (string, required): Knowledge base ID
- `newName` (string, required): New category name

### `delete_category` (~49 tokens)

Delete category

Delete a category from a knowledge base (uncategorizes all articles with that category)

Input parameters:

- `categoryName` (string, required): Category name to delete
- `knowledgeBaseId` (string, required): Knowledge base ID

### `list_comments` (~34 tokens)

List comments

List comments for an article

Input parameters:

- `articleId` (string, required): Article ID
- `status` (string): Filter by status

### `approve_comment` (~32 tokens)

Approve comment

Approve a pending comment on an article so it is shown publicly

Input parameters:

- `commentId` (string, required): Comment ID

### `reject_comment` (~32 tokens)

Reject comment

Reject a pending comment on an article so it is not shown publicly

Input parameters:

- `commentId` (string, required): Comment ID

### `delete_comment` (~25 tokens)

Delete comment

Delete a comment (soft delete)

Input parameters:

- `commentId` (string, required): Comment ID

### `list_article_versions` (~26 tokens)

List article versions

List all versions of an article

Input parameters:

- `articleId` (string, required): Article ID

### `restore_article_version` (~39 tokens)

Restore article version

Restore an article to a specific version

Input parameters:

- `articleId` (string, required): Article ID
- `versionNumber` (number, required): Version number to restore

## Diagnostics

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

## Score history

- 2026-11-06: 77
- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 76
- 2026-11-02: 76
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 71

## Common questions

### What is the Dedox MCP server?

Dedox is an MCP server listed in the public MCP registry as ai.dedox/dedox. Gives AI assistants read access to your Dedox help centre and knowledge base articles. This page covers its hosted endpoint (https://api.dedox.ai/mcp).

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

Dedox scores 77 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 Dedox MCP server expose?

Dedox exposes 24 tools: list_articles, get_article, create_article, update_article, delete_article, and 19 more. Their descriptions and schemas cost roughly 1,293 tokens of context every time the server is loaded.

### Does the Dedox MCP server require authentication?

Yes. Dedox asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Dedox MCP server still maintained?

Dedox is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Dedox MCP server?

VerifyMCP ran 13 checks on Dedox, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.dedox.ai/mcp
- Authorisation metadata: https://api.dedox.ai/.well-known/oauth-protected-resource/mcp
- Website: https://dedox.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-dedox-dedox/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-dedox-dedox/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-dedox-dedox/api.json
- HTML version of this page: https://verifymcp.io/servers/ai-dedox-dedox/api