Live survey286 models · 13 providers · 19,992 auditsAudited verification-before-completion · SAFE →What changedHow we verifyllms.txt

MCP server · Org-owned · Audited from source

AnomalyArmor MCP server

by anomalyarmor/agentsMIT licenceAudited 19 Sep 2026 · source 32edd5531688

PyPI armor-mcp 0.9.1stdiostreamable-http★ 2
!CAUTIONGrade B · 86/100 · 19 Sep 2026 · 32edd55
2GitHub stars
InstallView source on GitHub ↗

Is it safe? With care — CAUTION, grade B (86/100). The tool list is built at runtime, so we cannot read it from the source. The audit recorded 4 findings (0 critical, 1 high, 1 medium, 2 low). Maintainer's description: AI skills and MCP server for AnomalyArmor data observability

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “AnomalyArmor MCP server (anomalyarmor/agents)”. Retrieved 19 Sep 2026. https://modelsatlas.com/mcp/anomalyarmor/armor-mcp

Trust audit

Audit 0.4.1 · full source read 19 Sep 2026

Trust score86/100!CAUTION B
0 critical1 high1 medium2 low0 info

4 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.

What the source does

  • FilesystemNone observedNothing seen in the source
  • NetworkDeclared3 observations
  • ShellDeclared1 observation
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

“Declared” means the server says it does this and the source agrees. Browser, file and shell access are expected of some kinds of server.

Five audit layers

LayerWhat we checkResult
L0 ProvenanceRepo owner, licence, archive status, activityPASS 1 finding
L1 Static sourceSecrets, path traversal, supply chainWARN 1 finding
L2 InstructionsPrompt injection and authority framing in docs and tool descriptionsFAIL 1 finding
L3 InventoryDeclared tools match the sourcePASS 1 finding
L4 SandboxRun in isolation and watch behaviourSKIPPED

Provenance & runtime

Who published it, and what the audit could and could not run

Provenance

  • Repository owner anomalyarmorOrganizationAccount type recorded when we read the repository.
  • PackagePublished on PyPIarmor-mcp at version 0.9.1
  • LicenceMITFrom the repository, as read at the audited commit.
  • Last push4 months agoActivity of the repository when we read it.
  • Source commit read32edd5531688The audit covers exactly this commit, read on 19 Sep 2026.

Runtime

  • Sandbox runNot run yetThis audit read the source only; it did not execute the server.
  • Tool inventoryBuilt at runtimeThe source declares no tools; the server lists them when a client connects, so we cannot read them.

Every value here is read from the record's own repository and audit.Suggest a correction

Findings (4)

Sorted by severity

HIGHPrompt injectionprompt.credential_read · skills/connect/SKILL.md:43
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
2. Collect connection configuration (credentials, host, database, etc.)
Why
asks the agent to read credentials
Fix
—
MEDIUMCode injectioncode.dynamic_import · armor-mcp/src/armor_mcp/apps/runner.py:211
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
return importlib.import_module(f"{_TEMPLATE_PACKAGE}.{module_name}")
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenancemcp.no_tools_extracted · armor-mcp/server.json
F-13 Inventory / provenanceCWE-1104Layer L3
Why
the tool list is enumerated at runtime by tools/list, not declared in source
Fix
the page says so rather than showing an empty table

Tools it exposes

None declared in source

The tool list is built at runtime, so we cannot read it from the source.

Install

Package version 0.9.1 · audited commit 32edd55

Read the findings first. The most severe is Prompt injection (high) at skills/connect/SKILL.md.

No connect command is recorded for this server yet. Follow the repository's own instructions, and read the findings above first.

Audit history

  1. !CAUTION B 86 / 100

    Source changed, verdict held · 32edd5531688

README badge

For maintainers · updates on every re-audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B 
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/mcp/anomalyarmor/armor-mcp/badge.svg)](https://modelsatlas.com/mcp/anomalyarmor/armor-mcp/)

The badge always shows the latest audit; a maintainer cannot pin an old verdict.

Other ratings

Cited, never blended into our score

No third-party security ratings are recorded for this server yet. When they exist they appear here with their source and date, beside, not inside, our grade.

Questions about AnomalyArmor MCP server

What is the AnomalyArmor MCP server?
AI skills and MCP server for AnomalyArmor data observability
Is AnomalyArmor safe to connect to an agent?
With care. The audit graded it B (86/100) and found 4 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does AnomalyArmor need?
It reads ARMOR_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does AnomalyArmor run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as armor-mcp.
How current is this page?
The grade is for one exact copy of the source (32edd5531688), read on 2026-09-19. The repository is watched and re-audited when it changes.

Sources

  • anomalyarmor/agents on GitHub — the source we read, its licence, stars and activityObserved · 19 Sep 2026
  • ModelsAtlas trust audit — CAUTION verdict for commit 32edd5531688Observed · 19 Sep 2026

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.