# io.github.ExpertVagabond/watsonx (npm · watsonx-mcp-server)

IBM watsonx.ai MCP server for Claude integration

- Trust score: 62/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `watsonx-mcp-server`: 62/100 (this document), [markdown](https://verifymcp.io/servers/expertvagabond-watsonx/watsonx-mcp-server.md), [page](https://verifymcp.io/servers/expertvagabond-watsonx/watsonx-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `watsonx-mcp-server`
- Version: `1.0.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (151 of 152), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (151 of 152), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 169 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 837 tokens (~64/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% 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 expertvagabond-watsonx -- npx -y watsonx-mcp-server
```

### Codex

```bash
codex mcp add expertvagabond-watsonx -- npx -y watsonx-mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add expertvagabond-watsonx --command npx --arg -y --arg watsonx-mcp-server
```

### Hermes

```yaml
mcp_servers:
  expertvagabond-watsonx:
    command: "npx"
    args: ["-y", "watsonx-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "expertvagabond-watsonx": {
      "command": "npx",
      "args": [
        "-y",
        "watsonx-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 61, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 21, +5)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 16, −6)

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

### 2026-07-30 (score 22, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (13)

### `watsonx_generate` (~144 tokens)

Generate text using IBM watsonx.ai foundation models (Granite, Llama, Mistral, etc.)

Input parameters:

- `max_new_tokens` (number): Maximum number of tokens to generate
- `model_id` (string): Model ID (e.g., 'ibm/granite-3-3-8b-instruct', 'meta-llama/llama-3-70b-instruct')
- `prompt` (string, required): The prompt to send to the model
- `temperature` (number): Temperature for sampling (0-2)
- `top_k` (number): Top-k sampling
- `top_p` (number): Top-p nucleus sampling

### `watsonx_list_models` (~21 tokens)

List available foundation models in watsonx.ai

### `watsonx_embeddings` (~45 tokens)

Generate text embeddings using watsonx.ai embedding models

Input parameters:

- `model_id` (string): Embedding model ID
- `texts` (array, required): Array of texts to embed

### `watsonx_chat` (~59 tokens)

Have a conversation with watsonx.ai chat models

Input parameters:

- `max_new_tokens` (number)
- `messages` (array, required): Array of chat messages
- `model_id` (string): Chat model ID
- `temperature` (number)

### `key_protect_list_keys` (~52 tokens)

List encryption keys from IBM Key Protect (HSM-backed key management on IBM Z infrastructure)

Input parameters:

- `limit` (number): Maximum number of keys to return
- `offset` (number): Offset for pagination

### `key_protect_create_key` (~97 tokens)

Create a new encryption key in IBM Key Protect (stored in FIPS 140-2 Level 3 HSM)

Input parameters:

- `description` (string): Description of the key's purpose
- `extractable` (boolean): Whether the key material can be extracted
- `name` (string, required): Name for the new key
- `type` (string): Key type: root_key (for wrapping) or standard_key (for encryption)

### `key_protect_get_key` (~37 tokens)

Get details of a specific key from IBM Key Protect

Input parameters:

- `key_id` (string, required): The ID of the key to retrieve

### `key_protect_wrap_key` (~80 tokens)

Wrap (encrypt) data using a root key in IBM Key Protect - for envelope encryption

Input parameters:

- `aad` (array): Additional authentication data (AAD) for AEAD encryption
- `key_id` (string, required): The ID of the root key to use for wrapping
- `plaintext` (string, required): Base64-encoded data encryption key to wrap

### `key_protect_unwrap_key` (~78 tokens)

Unwrap (decrypt) data using a root key in IBM Key Protect

Input parameters:

- `aad` (array): Additional authentication data (must match wrap AAD)
- `ciphertext` (string, required): Base64-encoded wrapped data encryption key
- `key_id` (string, required): The ID of the root key to use for unwrapping

### `key_protect_delete_key` (~53 tokens)

Delete an encryption key from IBM Key Protect (irreversible)

Input parameters:

- `force` (boolean): Force deletion even if key has associated resources
- `key_id` (string, required): The ID of the key to delete

### `zos_connect_list_services` (~35 tokens)

List available z/OS Connect services (RESTful APIs to mainframe programs). Requires ZOS_CONNECT_URL to be configured.

### `zos_connect_call_service` (~93 tokens)

Call a z/OS Connect service to interact with mainframe programs (CICS, IMS, batch). Requires ZOS_CONNECT_URL to be configured.

Input parameters:

- `operation` (string): Operation/method to invoke (e.g., GET, POST)
- `payload` (object): JSON payload to send to the mainframe service
- `service_name` (string, required): Name of the z/OS Connect service to call

### `zos_connect_get_service_info` (~43 tokens)

Get detailed information about a z/OS Connect service including its OpenAPI specification

Input parameters:

- `service_name` (string, required): Name of the z/OS Connect service

## Diagnostics

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

## Score history

- 2026-08-03: 62
- 2026-08-02: 61
- 2026-08-01: 21
- 2026-07-31: 16
- 2026-07-30: 22
- 2026-07-28: 40
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/watsonx-mcp-server
- Socket report: https://socket.dev/npm/package/watsonx-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/expertvagabond-watsonx/watsonx-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/expertvagabond-watsonx/watsonx-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/expertvagabond-watsonx/watsonx-mcp-server