# LeakGuard (npm · @agentgate-builder/leakguard)

Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `api.youraitools.co`: 70/100, [markdown](https://verifymcp.io/servers/co-youraitools-leakguard/leakguard-mcp.md), [page](https://verifymcp.io/servers/co-youraitools-leakguard/leakguard-mcp)
- npm · `@agentgate-builder/leakguard`: 61/100 (this document), [markdown](https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard.md), [page](https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard)

## Channel facts

- Registry: `npm`
- Package: `@agentgate-builder/leakguard`
- Version: `0.1.0`
- 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 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 498 tokens (~249/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 75% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **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

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

LeakGuard runs locally as an npm package, launched with npx -y @agentgate-builder/leakguard. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add co-youraitools-leakguard -- npx -y @agentgate-builder/leakguard
```

### Cursor

```json
{
  "mcpServers": {
    "co-youraitools-leakguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentgate-builder/leakguard"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "co-youraitools-leakguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentgate-builder/leakguard"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add co-youraitools-leakguard -- npx -y @agentgate-builder/leakguard
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-youraitools-leakguard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agentgate-builder/leakguard"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add co-youraitools-leakguard --command npx --arg -y --arg @agentgate-builder/leakguard
```

### Hermes

```yaml
mcp_servers:
  co-youraitools-leakguard:
    command: "npx"
    args: ["-y", "@agentgate-builder/leakguard"]
```

### Netclaw

```json
{
  "McpServers": {
    "co-youraitools-leakguard": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@agentgate-builder/leakguard"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add co-youraitools-leakguard -t stdio -c npx -a -y @agentgate-builder/leakguard
```

### Other

```json
{
  "mcpServers": {
    "co-youraitools-leakguard": {
      "command": "npx",
      "args": [
        "-y",
        "@agentgate-builder/leakguard"
      ]
    }
  }
}
```

## 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.

### 2026-10-23 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-22 (score 46)

First indexed and scored.

## MCP tools (2)

### `scan_for_leaks` (~246 tokens)

Check text for leaked secrets before sending it

Runs locally and offline. Finds crypto wallet keys (BIP39 seed phrases with checksum, EVM and Solana private keys, WIF, xprv), API secrets (GitHub, AWS, Stripe, OpenAI, Anthropic, Slack, Telegram, npm, JWT, PEM, credentialed URLs, password= assignments) and PII (cards, IBAN, SSN, email, phone, IP). Returns verdict (WALLET_KEY_EXPOSED / SECRETS_FOUND / PII_FOUND / CLEAN), safe_to_send and findings with masked previews (never the secret). Pattern and validator based detection: it can miss secrets in unknown formats and can flag look-alikes. A clean result is not a guarantee.

Input parameters:

- `min_severity` (string)
- `style` (string): label: [REDACTED:type] (default); mask: keep last 4 digits / email domain for PII
- `text` (string, required): Text your agent is about to send to an LLM, tool, log or webhook
- `types` (array): Only these finding types or categories (wallet_key, secret, pii, email, ...)

### `redact_text` (~137 tokens)

Redact secrets, wallet keys and PII from text

Runs locally and offline. Same detection as scan_for_leaks, plus the redacted text ([REDACTED:type], or masked PII with style=mask) to send instead of the original.

Input parameters:

- `min_severity` (string)
- `style` (string): label: [REDACTED:type] (default); mask: keep last 4 digits / email domain for PII
- `text` (string, required): Text your agent is about to send to an LLM, tool, log or webhook
- `types` (array): Only these finding types or categories (wallet_key, secret, pii, email, ...)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard#diagnostics

## Score history

- 2026-10-23: 61
- 2026-10-22: 46

## Common questions

### What is the LeakGuard MCP server?

LeakGuard is an MCP server listed in the public MCP registry as co.youraitools/leakguard. Find and redact leaked secrets, wallet keys and PII before an AI agent sends text. This page covers its npm package (@agentgate-builder/leakguard).

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

LeakGuard scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. It declares no install or post-install scripts. 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 LeakGuard MCP server expose?

LeakGuard exposes 2 tools: scan_for_leaks, redact_text. Their descriptions and schemas cost roughly 383 tokens of context every time the server is loaded.

### Is the LeakGuard MCP server still maintained?

LeakGuard is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the LeakGuard MCP server under?

LeakGuard declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@agentgate-builder/leakguard
- Socket report: https://socket.dev/npm/package/@agentgate-builder/leakguard
- Website: https://youraitools.co/
- Changelog RSS feed: https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard.xml
- Changelog JSON feed: https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard.json
- HTML version of this page: https://verifymcp.io/servers/co-youraitools-leakguard/agentgate-builder-leakguard