# PromptGuard (oci · docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0)

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

- Trust score: 33/100 (low)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@promptguard/mcp-server`: 34/100, [markdown](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server.md), [page](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server)
- oci · `docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0`: 33/100 (this document), [markdown](https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0.md), [page](https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0)
- pypi · `promptguard-mcp-server`: 16/100, [markdown](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server-2.md), [page](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server-2)

## Channel facts

- Registry: `oci`
- Package: `docker.io/abhijoysarkar/promptguard-mcp-server: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 2026-08-03.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 6/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 119 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 480 tokens (~80/item across 6 items; 6 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add co-promptguard-security -- docker run --rm -i docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
```

### Codex

```bash
codex mcp add co-promptguard-security -- docker run --rm -i docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-promptguard-security": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  co-promptguard-security:
    command: "docker"
    args: ["run", "--rm", "-i", "docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0"]
```

### Other

```json
{
  "mcpServers": {
    "co-promptguard-security": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 33, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-07-31 (score 29, −3)

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

### 2026-07-27 (score 32, 0)

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

### 2026-07-26 (score 32)

First indexed and scored.

## MCP tools (6)

### `promptguard_auth` (~93 tokens)

Authenticate with PromptGuard. When called without an api_key, opens the PromptGuard dashboard in the browser so the user can copy their API key — then ask the user to provide it. When called with an api_key, validates and saves it.
When to use: When any other promptguard tool reports that the user is not authenticated, or when the user asks to log in.

Input parameters:

- `api_key` (string)

### `promptguard_logout` (~39 tokens)

Log out of PromptGuard by removing the locally stored API key and configuration.
When to use: When the user wants to switch accounts or clear credentials.

### `promptguard_scan_text` (~85 tokens)

Scan text for security threats including prompt injection, jailbreaks, PII leakage, and toxic content. Returns a decision (allow/block), confidence score, threat type, and reason.
When to use: When reviewing user-facing prompts, testing LLM inputs for safety, or verifying content is free of injection attacks before sending to an LLM.

Input parameters:

- `text` (string, required)

### `promptguard_scan_project` (~95 tokens)

Scan a project directory for unprotected LLM SDK usage (OpenAI, Anthropic, Cohere, Gemini, Bedrock, Mistral). Detects import statements and client instantiations.
When to use: After generating new code that uses LLM SDKs, when reviewing pull requests, or when auditing a codebase for security coverage gaps.

Input parameters:

- `directory` (string)
- `provider` (string)

### `promptguard_redact` (~89 tokens)

Redact PII (emails, phone numbers, SSNs, credit cards, API keys) from text. Returns sanitized text with entities replaced by placeholders like [EMAIL], [PHONE], [SSN].
When to use: Before including user data in LLM prompts, when processing customer messages, or when building RAG pipelines that ingest documents containing personal information.

Input parameters:

- `text` (string, required)

### `promptguard_status` (~46 tokens)

Show current PromptGuard configuration and status. Returns authentication state, API connectivity, and version.
When to use: To verify PromptGuard is properly configured or check which API endpoint is active.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0#diagnostics

## Score history

- 2026-08-03: 33
- 2026-08-02: 33
- 2026-08-01: 29
- 2026-07-31: 29
- 2026-07-30: 32
- 2026-07-29: 32
- 2026-07-28: 32
- 2026-07-27: 32
- 2026-07-26: 32

## Links

- Changelog RSS feed: https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0/changelog.json
- HTML version of this page: https://verifymcp.io/servers/co-promptguard-security/docker-io-abhijoysarkar-promptguard-mcp-server-1-0-0