Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AdversaryGate

PYPI · ADVERSARY-GATE-MCP

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

Available components

+3 this week 85 Trust /100

Last scanned (15 hours ago)

Scores higher than 88% of PyPI servers

Category Testing and QA

Trust breakdown (7 categories)

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 Security99
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 10 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Sanflow10/adversary-gate). View diagnostics → Pass
  • Clear OSI-approved license (AGPL-3.0-only).Pass
  • Actively maintained (last published 9 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability54
  • AI-judged instruction clarity (good).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management73
  • Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 4 Nov 26 +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.

  • 1 Nov 26 +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.

  • 31 Oct 26 0
    • Package version: 3.0.4 → 3.0.17 functional
  • 30 Oct 26 +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.

  • 28 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
  • 27 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 3.0.16 → 3.0.17 functional
  • 26 Oct 26 +1
    • Package version: 3.0.4 → 3.0.16 functional
  • 25 Oct 26 0
    • Tool safety: pass → unverified ▼ security
    • Stability: 0.33 → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Package version: 3.0.15 → 3.0.16 functional
Diagnostics

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 pypi/adversary-gate-mcp@3.0.17

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 pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo Sanflow10/adversary-gate
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Sanflow10/adversary-gate/.github/workflows/pypi-publish.yml@refs/tags/v3.0.17
Rekor log index 3510646527
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:eecc740110261dbabc4b171ad625bcf815c2be76b0c26576585b3abf689f7318

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 10 packages
Packages resolved 10
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 2 exposed · ~760 tokens

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 →

Tool Tokens
gate_policy ~185

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultobjectyes–

No examples provided.

verify_repo ~575

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…

NameTypeReqDescription
base_refstring––
claims–––
pytest_args–––
repostringyes–
timeout_secondsinteger––
NameTypeReqDescription
resultobjectyes–

No examples provided.

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.

pypi · adversary-gate-mcp

# add to Claude Code
claude mcp add sanflow10-adversary-gate -- uvx adversary-gate-mcp
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.