Publisher · GitHub organization

mcollina

github.com/mcollina ↗Last audit 29 Oct 2026

mcollina publishes 1 MCP server and 11 agent skills on the atlas: 9 SAFE, 2 CAUTION, 1 BLOCK, with a mean score of 87/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “mcollina: skills and MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/orgs/mcollina
Listings
12

1 MCP servers · 11 skills

Mean score
87 / 100

mean of the audit scores

Findings
22

across all listings

Stars
22K

on the listed repositories

✓SAFE 9!CAUTION 2✕BLOCK 1

Everything mcollina publishes here

Most stars first · stamps show the audited version

octocatmcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 28 Oct 2026
skill-optimizermcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 28 Oct 2026
typescript-magicianmcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 29 Oct 2026
nodejs-coremcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 26 Oct 2026
oauthmcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 27 Oct 2026
snipgraphermcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 28 Oct 2026
nodemcollina/skills
Skill ★ 2K
!CAUTIONB · 89 · 24 Oct 2026
fastify-best-practicesmcollina/skills
Skill ★ 2K
!CAUTIONB · 89 · 21 Oct 2026
initmcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 22 Oct 2026
Skill ★ 2K
✓SAFEB · 89 · 23 Oct 2026
documentationmcollina/skills
Skill ★ 2K
✓SAFEB · 89 · 20 Oct 2026
Ripgrepmcollina/mcp-ripgrep
MCP ★ 75
✕BLOCKD · 65 · 7 Oct 2026

Questions

Are mcollina's MCP servers and skills safe to install?
Of 12 listings, 9 are SAFE, 2 CAUTION and 1 BLOCK, with a mean score of 87 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 mcollina?
It collects every skill and MCP server on the atlas whose source lives under github.com/mcollina, 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.