Log inSubmit server
Clawguard MCP logo

Clawguard MCP

by joergmichno

Scans agent inputs for prompt injection with ClawGuard Shield’s 225-pattern detection API.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Clawguard MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "joergmichno-clawguard-mcp": {
      "command": "uvx",
      "args": [
        "clawguard-mcp"
      ],
      "env": {
        "CLAWGUARD_API_KEY": "YOUR_VALUE_HERE",
        "CLAWGUARD_BASE_URL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

joergmichno/clawguard-mcp connects MCP-compatible clients to the ClawGuard Shield API for prompt injection scanning. It provides single-text and batch scans, exposes the API’s detection patterns, reports quota usage, and checks service health. Reach for it when an agent workflow needs an external security check before processing untrusted text; it requires a Shield API key and network access.

Use cases

  • Scan untrusted agent input for prompt injection
  • Batch-check up to 10 text samples
  • Inspect detection patterns by category
  • Monitor Shield API quota
  • Verify Shield API availability

Key features

  • 225 prompt injection detection patterns
  • Single-text and batch scanning
  • Deterministic regular-expression detection
  • Risk scores, severity levels, and matched findings
  • Usage and health monitoring tools
  • Support for 15 languages

Tools5

What Clawguard MCP lets your agent do. Expand a tool for its parameters.

Self-reported~61 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 85d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · clawguard-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
Last commit18d agoMost recent push to the default branch.
Tools exposed5Callable tools this server registers over MCP.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Clawguard MCP works

What joergmichno/clawguard-mcp does

ClawGuard MCP makes ClawGuard Shield’s prompt injection scanner available through the Model Context Protocol. It is intended for use from Claude Desktop, Claude Code, Cursor, or another MCP-compatible client. Scan results can identify whether text is clean, provide a risk score and severity, and return matched findings such as instruction overrides.

The Shield API evaluates content against 225 detection patterns. Pattern categories include prompt injection, jailbreak attempts, data exfiltration, social engineering, and encoding attacks. The scanner supports 15 languages and maps individual patterns to OWASP LLM and Agentic Top 10 areas. Detection uses a deterministic regular-expression engine rather than an LLM round trip.

How it works

The MCP process receives tool calls from the connected client and sends scanning or account requests to ClawGuard Shield. scan_text handles one text value, while scan_batch accepts up to 10 texts in a single call. The server also exposes pattern information, quota status, and an API health check.

A typical request asks the client to scan text for prompt injection. The returned data may include an is_clean result, a numeric risk_score, a severity level, and findings with the matched pattern, category, severity, and text.

Setup and configuration

The package can be launched with uvx clawguard-mcp. Configure it as an MCP server and provide the required CLAWGUARD_API_KEY, which uses the cgs_ key format. The default Shield endpoint is https://prompttools.co/api/v1; set CLAWGUARD_BASE_URL when using another endpoint, including a self-hosted setup.

Claude Desktop configuration uses the command value uvx, the argument clawguard-mcp, and the API key in the server’s environment. Claude Code can add the server with claude mcp add clawguard -- uvx clawguard-mcp, followed by setting the key in the environment. A free Shield tier includes 100 scans per day.

For local development, the repository uses uv sync for installation and uv run pytest for tests. MCP Inspector can launch the local package for manual testing.

Tools and capabilities

  • scan_text: inspect one text for prompt injection threats.
  • scan_batch: inspect up to 10 texts in one request.
  • get_patterns: list the 225 detection patterns and their categories.
  • get_usage: view API consumption and remaining quota.
  • health_check: verify that the Shield API is available.

Limitations and notes

Scanning depends on access to the Shield API and a valid API key. The free tier limits usage to 100 scans per day. The repository is retained as a historical reference and identifies ModVet as its successor for pre-install scanning of Claude Code mods; ModVet is described as offline and deterministic, without an LLM.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Clawguard MCP

joergmichno/clawguard-mcp is an MCP server that connects to ClawGuard Shield, an API for detecting prompt injection threats. It provides scan_text and scan_batch for analysis, plus get_patterns, get_usage, and health_check for pattern discovery, quota checks, and service status from MCP-compatible clients.

Install it by launching `uvx clawguard-mcp` from your MCP client configuration. Claude Code can add it with `claude mcp add clawguard -- uvx clawguard-mcp`; then set the required `CLAWGUARD_API_KEY` environment variable.

Yes, it works with Cursor because the server is exposed through the Model Context Protocol. Configure Cursor to launch `uvx clawguard-mcp` and provide a valid ClawGuard Shield API key.

It requires a ClawGuard Shield key in `CLAWGUARD_API_KEY`, typically beginning with `cgs_`. The free tier provides 100 scans per day, and the server sends requests to the configured Shield API endpoint.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewClawguard MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/joergmichno-clawguard-mcp?style=directory)](https://allmcps.com/mcp/joergmichno-clawguard-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/joergmichno-clawguard-mcp"><img src="https://allmcps.com/api/badge/joergmichno-clawguard-mcp?style=directory" alt="Clawguard MCP on AllMCPs" /></a>