Publisher · GitHub organization

knuckles-team

github.com/knuckles-team ↗Last audit 11 Oct 2026

knuckles-team publishes 10 MCP servers on the atlas: 1 SAFE, 1 CAUTION, 8 BLOCK, with a mean score of 71/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “knuckles-team: skills and MCP servers”. Retrieved 11 Oct 2026. https://modelsatlas.com/orgs/knuckles-team
Listings
10

10 MCP servers · 0 skills

Mean score
71 / 100

mean of the audit scores

Findings
159

across all listings

Stars
40

on the listed repositories

SAFE 1CAUTION 1BLOCK 8

Everything knuckles-team publishes here

Most stars first · stamps show the audited version

servicenow-apiKnuckles-Team/servicenow-api
MCP ★ 20
✕BLOCKD · 69 · 10 Oct 2026
container-manager-mcpKnuckles-Team/container-manager-mcp
MCP ★ 6
✕BLOCKD · 67 · 11 Oct 2026
arr-mcpKnuckles-Team/arr-mcp
MCP ★ 5
✕BLOCKD · 69 · 11 Oct 2026
audio-transcriberKnuckles-Team/audio-transcriber
MCP ★ 3
✕BLOCKD · 69 · 11 Oct 2026
systems-managerKnuckles-Team/systems-manager
MCP ★ 3
✕BLOCKD · 69 · 11 Oct 2026
documentdb-mcpKnuckles-Team/documentdb-mcp
MCP ★ 2
✕BLOCKD · 69 · 11 Oct 2026
mealie-mcpKnuckles-Team/mealie-mcp
MCP ★ 1
!CAUTIONC · 79 · 11 Oct 2026
microsoft-agentKnuckles-Team/microsoft-agent
MCP
✓SAFEB · 84 · 11 Oct 2026
leanix-agentKnuckles-Team/leanix-agent
MCP
✕BLOCKD · 69 · 11 Oct 2026
portainer-agentKnuckles-Team/portainer-agent
MCP
✕BLOCKD · 69 · 11 Oct 2026

Questions

Are knuckles-team's MCP servers safe to install?
Of 10 listings, 1 are SAFE, 1 CAUTION and 8 BLOCK, with a mean score of 71 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about knuckles-team?
It collects every skill and MCP server on the atlas whose source lives under github.com/knuckles-team, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

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