# io.github.usezn/zn-gate (npm · zn-gate)

The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.

- Trust score: 91/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `zn-gate`: 91/100 (this document), [markdown](https://verifymcp.io/servers/usezn-zn-gate/zn-gate.md), [page](https://verifymcp.io/servers/usezn-zn-gate/zn-gate)

## Channel facts

- Registry: `npm`
- Package: `zn-gate`
- Version: `1.14.1`
- 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**: 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.
  - 0 of 8 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to usezn/zn).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 699 tokens (~174/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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.

## Install

### How do I install the io.github.usezn/zn-gate MCP server?

io.github.usezn/zn-gate runs locally as an npm package, launched with npx -y zn-gate. 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 usezn-zn-gate -- npx -y zn-gate
```

### Cursor

```json
{
  "mcpServers": {
    "usezn-zn-gate": {
      "command": "npx",
      "args": [
        "-y",
        "zn-gate"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "usezn-zn-gate": {
      "command": "npx",
      "args": [
        "-y",
        "zn-gate"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add usezn-zn-gate -- npx -y zn-gate
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "usezn-zn-gate": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "zn-gate"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add usezn-zn-gate --command npx --arg -y --arg zn-gate
```

### Hermes

```yaml
mcp_servers:
  usezn-zn-gate:
    command: "npx"
    args: ["-y", "zn-gate"]
```

### Netclaw

```json
{
  "McpServers": {
    "usezn-zn-gate": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "zn-gate"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add usezn-zn-gate -t stdio -c npx -a -y zn-gate
```

### Other

```json
{
  "mcpServers": {
    "usezn-zn-gate": {
      "command": "npx",
      "args": [
        "-y",
        "zn-gate"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 88, +4)

- [security regression] Stability: 0.40 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] MCP protocol: fail → pass
- [functional] Schema quality: good → excellent
- [functional] Package version: 1.13.1 → 1.14.1

### 2026-10-27 (score 84, +1)

- [functional] Package version: 1.6.0 → 1.13.1

### 2026-10-24 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 81, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (4)

### `analyze_prompt` (~192 tokens)

Check text for prompt injection

Check a piece of text for prompt injection, jailbreak attempts, role hijacking and attempts to steal credentials. Use it on a user message, system prompt or message from another agent that should be checked before you act on it. The check runs on this computer. Only if the user has turned on the optional cloud check (ZN_CLOUD=1 with ZN_API_KEY, or zn-gate connect) is the text, with secrets removed, also sent to the zn cloud. Returns a verdict (allow or block), a confidence score and the rule that matched. Example input: {"text": "Summarize the meeting notes below."}

Input parameters:

- `text` (string, required): The full text to check: a user message, a system prompt, or a message from another agent or tool. Send the whole text, not a summary. Text is checked as-is; a missing or non-text value is treated as…

### `check_tool_call` (~227 tokens)

Check a tool call before it runs

Check a tool call before it runs. Call it with the tool name and its arguments right before the agent executes the tool, for example a shell command, a file write, a database query or a message to send. It runs the local rules on the arguments and looks for injected instructions, sensitive file paths and links that would send data out. It does not judge whether a command is destructive. Nothing leaves the computer. Returns safe_to_execute, the verdict (allow or block) and the arguments with sensitive values hidden. Example input: {"tool_name": "write_file", "arguments": {"path": "notes.txt", "content": "hello"}}

Input parameters:

- `arguments` (object, required): The arguments the agent will pass to the tool, as a JSON object (for example {"command": "ls -la"}). Send exactly what the tool would receive. Nested objects and arrays are fine.
- `tool_name` (string, required): The name of the tool the agent is about to run, exactly as the agent calls it (for example bash, write_file, execute_sql or send_message).

### `check_tool_result` (~208 tokens)

Check a tool result before the model reads it

Check the output of a tool before the model reads it. Call it on content that came from outside: web pages, search results, file contents, git commits, database query results and API responses. It looks for hidden instructions aimed at the model (indirect prompt injection) and for secrets such as API keys. Nothing leaves the computer. Returns the content with secrets redacted, or neutralized if an injection is found, plus the verdict. Example input: {"tool_name": "web_search", "content": "Search results here"}

Input parameters:

- `content` (string, required): The output the tool returned, as text. Markdown and JSON are fine. Send the whole output, since a partial check can miss an injection placed at the end. Structured values are also accepted and are ch…
- `tool_name` (string, required): The name of the tool that produced this output, for example fetch, web_search or read_file. It labels the result; it is not a permission list.

### `zn_status` (~72 tokens)

zn-gate status

Report the current zn-gate status: the detection engine, the rules version, and whether anything leaves this computer (and if so, what). Call it when the user asks what zn-gate is doing or whether their data is shared. It takes no arguments and changes nothing. Example: call it with no arguments.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/usezn-zn-gate/zn-gate#diagnostics

## Score history

- 2026-11-05: 91
- 2026-11-04: 91
- 2026-11-03: 91
- 2026-11-02: 90
- 2026-11-01: 90
- 2026-10-31: 89
- 2026-10-30: 89
- 2026-10-29: 88
- 2026-10-28: 88
- 2026-10-27: 84
- 2026-10-26: 83
- 2026-10-25: 83
- 2026-10-24: 83
- 2026-10-23: 82
- 2026-10-22: 82
- 2026-10-21: 81
- 2026-10-20: 66
- 2026-10-19: 80
- 2026-10-18: 80
- 2026-10-17: 53
- 2026-10-16: 67
- 2026-10-15: 52
- 2026-10-14: 50
- 2026-10-13: 50
- 2026-10-12: 50

## Common questions

### What is the io.github.usezn/zn-gate MCP server?

io.github.usezn/zn-gate is an MCP server listed in the public MCP registry as io.github.usezn/zn-gate. The local security layer for coding agents: secret redaction, injection checks and an MCP proxy. This page covers its npm package (zn-gate).

### Is the io.github.usezn/zn-gate MCP server safe to use?

io.github.usezn/zn-gate scores 91 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 io.github.usezn/zn-gate MCP server expose?

io.github.usezn/zn-gate exposes 4 tools: analyze_prompt, check_tool_call, check_tool_result, zn_status. Their descriptions and schemas cost roughly 699 tokens of context every time the server is loaded.

### Is the io.github.usezn/zn-gate MCP server still maintained?

io.github.usezn/zn-gate 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 licence is the io.github.usezn/zn-gate MCP server under?

io.github.usezn/zn-gate 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/zn-gate
- Socket report: https://socket.dev/npm/package/zn-gate
- Repository: https://github.com/usezn/zn
- Website: https://usezn.com/
- Changelog RSS feed: https://verifymcp.io/servers/usezn-zn-gate/zn-gate.xml
- Changelog JSON feed: https://verifymcp.io/servers/usezn-zn-gate/zn-gate.json
- HTML version of this page: https://verifymcp.io/servers/usezn-zn-gate/zn-gate