io.github.usezn/zn-gate
NPM · ZN-GATE
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
Available components
Last scanned (52 minutes ago)
Scores higher than 94% of npm servers
Category Security
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 → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 0 of 8 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to usezn/zn). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 5 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- AI-judged instruction clarity (excellent).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
- 3 Nov 26 +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.
- 1 Nov 26 +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.
- 30 Oct 26 +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.
- 28 Oct 26 +4
- Stability: 0.40 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: pass → fail ▼ functional
- MCP protocol: fail → pass ▲ functional
- Schema quality: good → excellent functional
- Package version: 1.13.1 → 1.14.1 functional
- 27 Oct 26 +1
- Package version: 1.6.0 → 1.13.1 functional
- 24 Oct 26 +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.
- 22 Oct 26 +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.
- 21 Oct 26 +15
- Malware scan: unverified → pass ▲ security
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 5 Nov 2026 · Analysed npm/zn-gate@1.14.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | usezn/zn |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/usezn/zn/.github/workflows/release.yml@refs/tags/v1.14.1 |
| Rekor log index | 3544509011 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:24436e8fc2992d6d57feb3ba66e23d0309521a9b18679c86048275e7e447a71e8e6a58e10270a35f17477c203b0c4631a7b2ef0d754cfa9b86181c0c9 |
Background: How many MCP packages publish verified provenance →
Dependencies 8 packages
| Packages resolved | 8 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
analyze_prompt Check text for prompt injection ~192
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."}
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | 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… |
No output schema declared.
No examples provided.
check_tool_call Check a tool call before it runs ~227
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"}}
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | yes | 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 | yes | 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). |
No output schema declared.
No examples provided.
check_tool_result Check a tool result before the model reads it ~208
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"}
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | 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 | yes | 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. |
No output schema declared.
No examples provided.
zn_status zn-gate status ~72
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
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.
npm · zn-gate
claude mcp add usezn-zn-gate -- npx -y zn-gate
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.