# AdversaryGate (pypi · adversary-gate-mcp)

Fail-closed merge gate an agent calls before saying done: MERGE, BLOCK or INCONCLUSIVE.

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `adversary-gate-mcp`: 85/100 (this document), [markdown](https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp.md), [page](https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp)

## Channel facts

- Registry: `pypi`
- Package: `adversary-gate-mcp`
- Version: `3.0.17`
- 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**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 1 of 10 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Sanflow10/adversary-gate).
  - Clear OSI-approved license (AGPL-3.0-only).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 842 tokens (~421/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**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **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 current MCP spec version (2026-07-28).

## Install

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

AdversaryGate runs locally as a PyPI package, launched with uvx adversary-gate-mcp. 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 sanflow10-adversary-gate -- uvx adversary-gate-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sanflow10-adversary-gate": {
      "command": "uvx",
      "args": [
        "adversary-gate-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sanflow10-adversary-gate": {
      "command": "uvx",
      "args": [
        "adversary-gate-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sanflow10-adversary-gate -- uvx adversary-gate-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sanflow10-adversary-gate": {
      "type": "local",
      "command": [
        "uvx",
        "adversary-gate-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sanflow10-adversary-gate --command uvx --arg adversary-gate-mcp
```

### Hermes

```yaml
mcp_servers:
  sanflow10-adversary-gate:
    command: "uvx"
    args: ["adversary-gate-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sanflow10-adversary-gate": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "adversary-gate-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sanflow10-adversary-gate -t stdio -c uvx -a adversary-gate-mcp
```

### Other

```json
{
  "mcpServers": {
    "sanflow10-adversary-gate": {
      "command": "uvx",
      "args": [
        "adversary-gate-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 83, 0)

- [functional] Package version: 3.0.4 → 3.0.17

### 2026-10-30 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 82, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-27 (score 66, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 3.0.16 → 3.0.17

### 2026-10-26 (score 81, +1)

- [functional] Package version: 3.0.4 → 3.0.16

### 2026-10-25 (score 80, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.33 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 3.0.15 → 3.0.16

## MCP tools (2)

### `verify_repo` (~575 tokens)

Verify a repository change

Judge the working tree of a git repository against a baseline, by running its tests.

When to call: after changing code in ``repo`` and before reporting the task
as done. Call ``gate_policy`` first if you need to know the floors or
whether the baseline is pinned. Python/pytest only; changes in other
languages come back inconclusive.

What it does: writes the baseline commit's tree (every file as committed),
diffs it against the working tree (uncommitted and untracked files
included), runs the suite under coverage.py, then runs the gate: the
claims on the baseline and on the patch, the baseline's copy of any test
the patch rewrote, and mutation testing on the changed lines. Nothing is
committed or reverted.

Side effects: the repository's tests execute -- its code runs, so they may
do whatever they do when you run pytest yourself. The coverage run uses the
repository as working directory; the gate's own files go to a temporary
directory that is removed afterwards. It can take minutes. A run longer
than ``timeout_seconds`` (default 3600: the gate's own full-suite run may
take 900 alone) returns inconclusive, never a pass, and its
\``next_steps`` names ``timeout_seconds`` as the limit to raise.

Arguments: ``repo`` is a path inside the git repository. ``claims`` are
pytest node ids (``path::test``) to verify; empty -> discovered from the
tests that executed a changed line. ``pytest_args`` are test paths or node
ids the coverage run collects (default: the whole suite); options such as
\``-k`` are refused. ``base_ref`` is used only when the operator did not pin
ADVERSARY_GATE_BASE_REF.

Returns ``decision`` (merge / block / inconclusive), ``mergeable``,
\``fix_proven``, ``reason``, per-claim results with the oracle used,
\``diff_coverage``, ``suite_strength``, ``next_steps`` and the full
artefact. merge permits a human review, not a release; block means fix the
code, not the tests; inconclusive means something was not measured -- say
what. ``next_steps`` lists what would ea…

Input parameters:

- `base_ref` (string)
- `claims`
- `pytest_args`
- `repo` (string, required)
- `timeout_seconds` (integer)

Output parameters:

- `result` (object)

### `gate_policy` (~185 tokens)

Show the gate policy

Show the verification policy this server enforces: floors, baseline, interpreter, and what the caller may set.

When to call: before ``verify_repo``, to learn whether the baseline is
pinned by the operator or chosen by you, which interpreter runs the tests,
and which floors a merge has to clear -- or after an inconclusive or block
answer, to explain it.

Read-only and fast: it runs no tests and changes nothing. The policy comes
from the server's environment (ADVERSARY_GATE_POLICY, _BASE_REF, _PYTHON),
set by whoever configured the server; no tool can change it.

Returns ``version``, ``operator_flags``, ``defaults``, ``baseline``,
\``python`` and ``agent_controls`` (the arguments of ``verify_repo`` you
decide). An invalid operator policy returns ``error`` instead.

Output parameters:

- `result` (object)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp#diagnostics

## Score history

- 2026-11-05: 85
- 2026-11-04: 85
- 2026-11-03: 84
- 2026-11-02: 84
- 2026-11-01: 84
- 2026-10-31: 83
- 2026-10-30: 83
- 2026-10-29: 82
- 2026-10-28: 82
- 2026-10-27: 66
- 2026-10-26: 81
- 2026-10-25: 80
- 2026-10-24: 80
- 2026-10-23: 79
- 2026-10-22: 64
- 2026-10-21: 78
- 2026-10-20: 78
- 2026-10-19: 77
- 2026-10-18: 77
- 2026-10-17: 77
- 2026-10-16: 76
- 2026-10-15: 61
- 2026-10-14: 75
- 2026-10-13: 50
- 2026-10-12: 50
- 2026-10-09: 35

## Common questions

### What is the AdversaryGate MCP server?

AdversaryGate is an MCP server listed in the public MCP registry as io.github.Sanflow10/adversary-gate. Fail-closed merge gate an agent calls before saying done: MERGE, BLOCK or INCONCLUSIVE. This page covers its PyPI package (adversary-gate-mcp).

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

AdversaryGate scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 AdversaryGate MCP server expose?

AdversaryGate exposes 2 tools: verify_repo, gate_policy. Their descriptions and schemas cost roughly 760 tokens of context every time the server is loaded.

### Is the AdversaryGate MCP server still maintained?

AdversaryGate 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 AdversaryGate MCP server under?

AdversaryGate declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the AdversaryGate MCP server?

VerifyMCP ran 16 checks on AdversaryGate, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/adversary-gate-mcp/
- Socket report: https://socket.dev/pypi/package/adversary-gate-mcp
- Repository: https://github.com/Sanflow10/adversary-gate
- Website: https://sanflow10.github.io/adversary-gate/
- Changelog RSS feed: https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sanflow10-adversary-gate/adversary-gate-mcp