# PromptGuard (oci · ghcr.io/promptguardhq/promptguard-mcp-server)

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

- Trust score: 36/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.promptguard.co`: 68/100, [markdown](https://verifymcp.io/servers/co-promptguard-security/api.md), [page](https://verifymcp.io/servers/co-promptguard-security/api)
- npm · `@promptguard/mcp-server`: 23/100, [markdown](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server.md), [page](https://verifymcp.io/servers/co-promptguard-security/promptguard-mcp-server)
- oci · `ghcr.io/promptguardhq/promptguard-mcp-server`: 36/100 (this document), [markdown](https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server.md), [page](https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/promptguardhq/promptguard-mcp-server`
- Version: `1.2.2`
- 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 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **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 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 84/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 674 tokens (~112/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 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.
  - Structured output schemas are declared (67% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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

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

PromptGuard runs locally as a container image, launched with docker run --rm -i -e PROMPTGUARD_API_KEY ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add co-promptguard-security -- docker run --rm -i -e PROMPTGUARD_API_KEY ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Cursor

```json
{
  "mcpServers": {
    "co-promptguard-security": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "PROMPTGUARD_API_KEY",
        "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"
      ]
    }
  }
}
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### VS Code

```json
{
  "servers": {
    "co-promptguard-security": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "PROMPTGUARD_API_KEY",
        "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"
      ]
    }
  }
}
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Codex

```bash
codex mcp add co-promptguard-security -- docker run --rm -i -e PROMPTGUARD_API_KEY ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-promptguard-security": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "PROMPTGUARD_API_KEY",
        "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"
      ],
      "enabled": true
    }
  }
}
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Hermes

```yaml
mcp_servers:
  co-promptguard-security:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "PROMPTGUARD_API_KEY", "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"]
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Netclaw

```json
{
  "McpServers": {
    "co-promptguard-security": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "PROMPTGUARD_API_KEY",
        "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"
      ]
    }
  }
}
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

### Other

```json
{
  "mcpServers": {
    "co-promptguard-security": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "PROMPTGUARD_API_KEY",
        "ghcr.io/promptguardhq/promptguard-mcp-server:1.2.2"
      ]
    }
  }
}
```

This image reads PROMPTGUARD_API_KEY. Set it in your client's env block for this server; docker run -e passes it through to the container.

## 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 36, +2)

- [security regression] Stability: 0.10 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Schema quality: 98 → 112
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional improvement] MCP protocol: fail → pass
- [functional] First check of Tool coverage: 67
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.1.3 → 1.2.2
- [functional] Package version: 1.1.3 → 1.2.1
- [functional] Package version: 1.1.3 → 1.2.0

### 2026-11-04 (score 34, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 33, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 32)

First indexed and scored.

## MCP tools (6)

### `promptguard_auth` (~122 tokens)

Connect PromptGuard

Check whether PromptGuard is authenticated, and if not, open the PromptGuard dashboard so the user can create an API key. This tool never takes the key itself: the user saves it outside the chat, by running `promptguard login` in a terminal or by setting PROMPTGUARD_API_KEY in this MCP server's configuration. Never ask the user to paste an API key into the conversation.
When to use: When any other promptguard tool reports that the user is not authenticated or not initialized, or when the user asks to log in to PromptGuard.

### `promptguard_logout` (~66 tokens)

Log out of PromptGuard

Log out of PromptGuard by removing the project-local configuration (.promptguard.json) and the globally stored API key (~/.promptguard/credentials.json).
When to use: When the user wants to switch PromptGuard accounts, clear credentials, or ensure a clean state by removing existing authentication.

### `promptguard_scan_text` (~129 tokens)

Scan text for threats

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. Each call counts as one Request on your PromptGuard plan.
When to use: When reviewing user-facing prompts, testing LLM inputs for safety, or verifying that content is free of injection attacks before sending to an LLM.

Input parameters:

- `content_type` (string): Whether the text is a prompt sent to a model or a model's response
- `text` (string, required): The text content to scan for security threats

Output parameters:

- `blocked` (boolean)
- `confidence` (number)
- `decision` (string)
- `eventId` (string|null)
- `flagged` (boolean)
- `processingTimeMs` (number|null)
- `reason` (string)
- `threatType` (string|null)

### `promptguard_scan_project` (~142 tokens)

Find unprotected LLM calls

Performs static analysis on a project directory to detect unprotected LLM SDK usage (OpenAI, Anthropic, Cohere, Gemini, Bedrock, etc.). Returns detected providers, file locations (line/column), and instance count.
When to use: During local development to find LLM calls that are not routed through PromptGuard, after generating new code that uses LLM SDKs, or when auditing an existing project for security coverage.

Input parameters:

- `directory` (string): Absolute path to the project directory to scan (defaults to current directory)
- `provider` (string): Filter results to a specific provider (e.g. 'openai', 'anthropic')

Output parameters:

- `files_scanned` (integer)
- `providers` (array)
- `summary` (string)

### `promptguard_redact` (~140 tokens)

Redact PII

Redact PII (emails, phone numbers, SSNs, credit cards, API keys) from text. Returns sanitized text with each entity replaced by a labeled placeholder, e.g. [EMAIL_REDACTED], [PHONE_REDACTED], [SSN_REDACTED], and the PII types found. Never returns the original text. Each call counts as one Request on your PromptGuard plan.
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): The text content to redact PII from

Output parameters:

- `piiFound` (array)
- `redacted` (string)

### `promptguard_status` (~75 tokens)

PromptGuard status

Show whether PromptGuard is set up and signed in, with this server's version and the account or configuration details it knows (the hosted server reports your plan; the local CLI server reports its key type, proxy URL and providers).
When to use: To verify PromptGuard is properly configured, or to confirm which version is running.

Output parameters:

- `api_key_type` (string)
- `initialized` (boolean)
- `message` (string)
- `providers` (array)
- `proxy_url` (string)
- `version` (string)

## Diagnostics

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

## Score history

- 2026-11-05: 36
- 2026-11-04: 34
- 2026-11-03: 33
- 2026-11-02: 33
- 2026-11-01: 32

## Common questions

### What is the PromptGuard MCP server?

PromptGuard is an MCP server listed in the public MCP registry as co.promptguard/security. Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client. This page covers its container image (ghcr.io/promptguardhq/promptguard-mcp-server).

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

PromptGuard scores 36 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 PromptGuard MCP server expose?

PromptGuard exposes 6 tools: promptguard_auth, promptguard_logout, promptguard_scan_text, promptguard_scan_project, promptguard_redact, promptguard_status. Their descriptions and schemas cost roughly 674 tokens of context every time the server is loaded.

### Is the PromptGuard MCP server still maintained?

PromptGuard 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.

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

VerifyMCP ran 11 checks on PromptGuard, covering Source repository, Provenance, License, Maintenance and 7 more. 5 items could not be completed, a gap on our side rather than a finding about PromptGuard: Malware scan, Known CVEs, Install scripts, Dependency health and 1 more. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- GitHub Container Registry: https://ghcr.io/promptguardhq/promptguard-mcp-server
- Website: https://promptguard.co/
- Changelog RSS feed: https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/co-promptguard-security/ghcr-io-promptguardhq-promptguard-mcp-server