# io.github.mrfentmen/exavault-mcp (npm · exavault-mcp)

MCP server for ExaVault: files, folders, shar MCP: real tools for real work.

- Trust score: 69/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `exavault-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp.md), [page](https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp)

## Channel facts

- Registry: `npm`
- Package: `exavault-mcp`
- Version: `1.0.0`
- 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 zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **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 19 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1278 tokens (~53/item across 24 items; 24 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 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**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_resources" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 24 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 io.github.mrfentmen/exavault-mcp server?

io.github.mrfentmen/exavault-mcp runs locally as an npm package, launched with npx -y exavault-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 mrfentmen-exavault-mcp -- npx -y exavault-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mrfentmen-exavault-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "exavault-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mrfentmen-exavault-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "exavault-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mrfentmen-exavault-mcp -- npx -y exavault-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add mrfentmen-exavault-mcp --command npx --arg -y --arg exavault-mcp
```

### Hermes

```yaml
mcp_servers:
  mrfentmen-exavault-mcp:
    command: "npx"
    args: ["-y", "exavault-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mrfentmen-exavault-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "exavault-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mrfentmen-exavault-mcp -t stdio -c npx -a -y exavault-mcp
```

### Other

```json
{
  "mcpServers": {
    "mrfentmen-exavault-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "exavault-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.

### 2026-11-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 67, +4)

- [functional improvement] Stability: unverified → 0.30

### 2026-11-10 (score 63, +5)

- [security improvement] Source repository: unverified → pass

### 2026-11-09 (score 58, +10)

- [security regression] Provenance: pass → unverified
- [security improvement] Malware scan: unverified → pass

### 2026-11-08 (score 48)

First indexed and scored.

## MCP tools (24)

### `get_account` (~33 tokens)

Read the ExaVault account behind the configured API credentials: company, contact details, plan, storage quota and user count.

### `update_account` (~90 tokens)

Update account settings such as company name, contact name, email, phone or timezone. Only the fields you pass are sent.

Input parameters:

- `company` (string): Company name
- `contactName` (string): Account contact name
- `email` (string): Contact email address
- `phone` (string): Contact phone number
- `timezone` (string): Timezone name, for example America/New_York

### `list_resources` (~111 tokens)

List files and folders at a path in the ExaVault account, optionally sorted and paged.

Input parameters:

- `limit` (integer): Maximum rows to return
- `offset` (integer): Rows to skip, for paging
- `path` (string): Folder path, for example / or /Clients/Acme. Defaults to the account root
- `sortBy` (string): Field to sort by, for example name, size or modified
- `sortOrder` (string): Sort direction: asc or desc

### `list_folder_contents` (~81 tokens)

List the contents of one folder by its ExaVault resource id, which is what the account UI and share links use.

Input parameters:

- `id` (integer, required): ExaVault resource id of the folder
- `sortBy` (string): Field to sort by, for example name or modified
- `sortOrder` (string): Sort direction: asc or desc

### `get_resource` (~62 tokens)

Read the properties of a single file or folder: type, size, uploader and timestamps.

Input parameters:

- `path` (string, required): Full path of the resource, for example /Clients/Acme/report.pdf
- `type` (string): Resource type hint: file or folder

### `create_folder` (~45 tokens)

Create a new folder inside an existing folder path.

Input parameters:

- `name` (string, required): Name of the new folder
- `path` (string, required): Parent folder path, for example /Clients

### `delete_resources` (~63 tokens)

Destructively delete a file or folder at a path. Set recursive to true to delete a folder and everything inside it.

Input parameters:

- `path` (string, required): Path of the file or folder to delete
- `recursive` (boolean): Delete a folder and all of its contents

### `copy_resources` (~61 tokens)

Copy one or more files or folders to a destination folder path inside the same account.

Input parameters:

- `destinationPath` (string, required): Destination folder path, for example /Archive
- `resources` (array, required): Source paths, for example ['/a/b.pdf', '/a/c']

### `move_resources` (~51 tokens)

Move one or more files or folders to a destination folder path. The source paths no longer exist afterwards.

Input parameters:

- `destinationPath` (string, required): Destination folder path
- `resources` (array, required): Source paths to move

### `compress_resources` (~66 tokens)

Zip one or more resources into a single archive stored at a destination folder path.

Input parameters:

- `destinationPath` (string, required): Folder where the archive is written
- `name` (string): Archive file name, for example bundle.zip
- `resources` (array, required): Paths to include in the archive

### `extract_resources` (~43 tokens)

Extract one or more zip archives into a destination folder path.

Input parameters:

- `destinationPath` (string, required): Folder to extract into
- `resources` (array, required): Archive paths to extract

### `get_download_url` (~39 tokens)

Get a direct download URL for a file so it can be fetched outside the API.

Input parameters:

- `path` (string, required): Path of the file to download

### `get_preview_url` (~56 tokens)

Get a preview URL for an image or document, optionally at a named thumbnail size.

Input parameters:

- `path` (string, required): Path of the file to preview
- `size` (string): Preview size, for example small, medium or large

### `list_email_lists` (~48 tokens)

List the email groups configured on the account, with their addresses and ids.

Input parameters:

- `limit` (integer): Maximum lists to return
- `offset` (integer): Lists to skip, for paging

### `create_email_list` (~48 tokens)

Create a new email group that receive forms and share notifications can be sent to.

Input parameters:

- `address` (string, required): Group email address
- `name` (string, required): Display name of the email group

### `get_email_list` (~26 tokens)

Read one email group by id.

Input parameters:

- `id` (integer, required): Email group id

### `delete_email_list` (~28 tokens)

Permanently delete an email group by id.

Input parameters:

- `id` (integer, required): Email group id

### `list_notifications` (~48 tokens)

List the event notifications configured on the account, such as upload or share alerts.

Input parameters:

- `limit` (integer): Maximum notifications to return
- `offset` (integer): Notifications to skip, for paging

### `create_notification` (~62 tokens)

Create an event notification that emails an address when a matching event happens.

Input parameters:

- `email` (string, required): Address to notify
- `message` (string): Custom message included in the notification
- `type` (string, required): Event type, for example upload, download or share

### `delete_notification` (~26 tokens)

Permanently delete an event notification by id.

Input parameters:

- `id` (integer, required): Notification id

### `get_session_activity` (~94 tokens)

Read the account's session activity log, optionally narrowed to a date range and event type.

Input parameters:

- `endDate` (string): End date, for example 2026-01-31
- `limit` (integer): Maximum rows to return
- `startDate` (string): Start date, for example 2026-01-01
- `type` (string): Activity type filter, for example login or upload

### `get_webhook_activity` (~37 tokens)

Read the webhook delivery log, which shows which outbound webhook calls the account made.

Input parameters:

- `limit` (integer): Maximum rows to return

### `list_forms` (~26 tokens)

List the receive forms on the account: the public upload pages that file into a folder.

### `get_form` (~34 tokens)

Read one receive form by id: its name, target path and submission count.

Input parameters:

- `id` (integer, required): Receive form id

## Diagnostics

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

## Score history

- 2026-11-21: 69
- 2026-11-20: 69
- 2026-11-19: 68
- 2026-11-18: 68
- 2026-11-17: 67
- 2026-11-16: 63
- 2026-11-15: 63
- 2026-11-14: 63
- 2026-11-13: 63
- 2026-11-12: 63
- 2026-11-11: 63
- 2026-11-10: 63
- 2026-11-09: 58
- 2026-11-08: 48

## Common questions

### What is the io.github.mrfentmen/exavault-mcp server?

io.github.mrfentmen/exavault-mcp is listed in the public MCP registry as io.github.mrfentmen/exavault-mcp. MCP server for ExaVault: files, folders, shar MCP: real tools for real work. This page covers its npm package (exavault-mcp).

### Is the io.github.mrfentmen/exavault-mcp server safe to use?

io.github.mrfentmen/exavault-mcp scores 69 out of 100 on VerifyMCP. We recorded 1 known advisory 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 io.github.mrfentmen/exavault-mcp server expose?

io.github.mrfentmen/exavault-mcp exposes 24 tools: get_account, update_account, list_resources, list_folder_contents, get_resource, and 19 more. Their descriptions and schemas cost roughly 1,278 tokens of context every time the server is loaded.

### Is the io.github.mrfentmen/exavault-mcp server still maintained?

io.github.mrfentmen/exavault-mcp 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 io.github.mrfentmen/exavault-mcp server under?

io.github.mrfentmen/exavault-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the io.github.mrfentmen/exavault-mcp server?

VerifyMCP ran 16 checks on io.github.mrfentmen/exavault-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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/exavault-mcp
- Socket report: https://socket.dev/npm/package/exavault-mcp
- Repository: https://github.com/mrfentmen/awesome-servers
- Changelog RSS feed: https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mrfentmen-exavault-mcp/exavault-mcp
