PromptGuard
OCI · DOCKER.IO/ABHIJOYSARKAR/PROMPTGUARD-MCP-SERVER:1.0.0 · 3 COMPONENTS · SCANNED AUG 3
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
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. How we score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- CVE data not yet available for this package.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency-health data not yet available.Unverified
Provenance & Transparency6
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 119 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 480 tokens (~80/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
oci · docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
claude mcp add co-promptguard-security -- docker run --rm -i docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
codex mcp add co-promptguard-security -- docker run --rm -i docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
{
"$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
}
}
} mcp_servers:
co-promptguard-security:
command: "docker"
args: ["run", "--rm", "-i", "docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0"] {
"mcpServers": {
"co-promptguard-security": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 2 Aug 26 +4
- Stability: unverified → 0.23 ▲ functional
- 31 Jul 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Jul 26 32
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 3 Aug 2026 · Analysed oci/docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0
Provenance none
Ecosystem: oci · Outcome: none
Reason: no_attestation
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
promptguard_auth ~93
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.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | — | — |
Structured output declared, but exposes no named fields.
No examples provided.
promptguard_logout ~39
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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
promptguard_redact ~89
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.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | — |
Structured output declared, but exposes no named fields.
No examples provided.
promptguard_scan_project ~95
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.
| Name | Type | Req | Description |
|---|---|---|---|
| directory | string | — | — |
| provider | string | — | — |
Structured output declared, but exposes no named fields.
No examples provided.
promptguard_scan_text ~85
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.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | — |
Structured output declared, but exposes no named fields.
No examples provided.
promptguard_status ~46
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.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.