← Index

AdversaryGate

io.github.Sanflow10/adversary-gatev3.0.14Other

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

The current version, v3.0.14, was published to the official MCP registry on 2026-10-19. It is distributed as adversary-gate-mcp on PyPI, filed under Other by this index, and declares 4 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using AdversaryGate in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Auditable install path →Watch it hold a drift →
Trust verdict · v1 advisory · method
REVIEWstatus: PARTIALfresh until 2026-11-05 05:03 UTC
screened 2026-10-06tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No malicious instructions”via static_description

Limits of this verdict
  • - Semantic screen only - the deterministic conformance probe has not run on this server
  • - Confidence is reported but not yet calibrated (v1)
  • - Screen reads the tool description, not the live behavior
  • - advisory
  • - registry description only no input schema
  • - screen model 8b
  • - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Test a description on the public screen → It is a separate check from the verdict above, so the two can differ.

That verdict was true at screening time (snapshot 2026-10-19).

Contracts can change after screening, with no version bump. The gate pins AdversaryGate’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Cite this record

People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.

Markdown
[Independent trust record for AdversaryGate](https://mcpindex.ai/server/io-github-sanflow10-adversary-gate) - screening verdict, registry provenance, and contract drift monitoring.
HTML
<a href="https://mcpindex.ai/server/io-github-sanflow10-adversary-gate">Independent trust record for AdversaryGate</a> - screening verdict, registry provenance, and contract drift monitoring.
Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown
[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-sanflow10-adversary-gate)](https://mcpindex.ai/server/io-github-sanflow10-adversary-gate)
HTML
<a href="https://mcpindex.ai/server/io-github-sanflow10-adversary-gate"><img src="https://mcpindex.ai/api/v1/badge/io-github-sanflow10-adversary-gate" alt="mcpindex verdict" height="20" /></a>
Environment variables
ADVERSARY_GATE_BASE_REF

Baseline git ref (e.g. origin/main). Unset, the agent may pick it, and whoever picks the baseline picks the oracle

ADVERSARY_GATE_REQUIRE_PINNED_BASE

Set to 1 to refuse any run without ADVERSARY_GATE_BASE_REF, so the agent can never choose the baseline (the oracle)

ADVERSARY_GATE_PYTHON

Interpreter that runs the tests; must be one the agent cannot write to

ADVERSARY_GATE_POLICY

Extra gate flags set by the operator; evidence flags are refused

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
10
Alternatives in Other
Ask Your Audience
ai.askyouraudience/ask-your-audience

Test ideas, messages and ads with Human Digital Twins built from real people, in your AI assistant.

BetSlip Doctor
ai.betslipdoctor/mcp

Bet slip grader: grade a parlay A+ to F- before you bet, track slips, history and Tail. 21+, US.

Brownfield Cartographer
io.github.Sanoy24/brownfield-cartographer

Local impact and table, column and Airflow lineage for SQL, dbt, Python and TypeScript repos.