Publisher · GitHub organization
modelcontextprotocol
github.com/modelcontextprotocol ↗Last audit 23 Oct 2026
modelcontextprotocol publishes 4 MCP servers and 4 agent skills on the atlas: 4 SAFE, 3 CAUTION, 1 BLOCK, with a mean score of 82/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
Cite
Cite this page
ModelsAtlas. “modelcontextprotocol: skills and MCP servers”. Retrieved 23 Oct 2026. https://modelsatlas.com/orgs/modelcontextprotocol
- Listings
- 8
- Mean score
- 82 / 100
- Findings
- 66
- Stars
- 31K
4 MCP servers · 4 skills
mean of the audit scores
across all listings
on the listed repositories
SAFE 4CAUTION 3BLOCK 1
Everything modelcontextprotocol publishes here
Most stars first · stamps show the audited version
Questions
Are modelcontextprotocol's MCP servers and skills safe to install?
Of 8 listings, 4 are SAFE, 3 CAUTION and 1 BLOCK, with a mean score of 82 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 modelcontextprotocol?
It collects every skill and MCP server on the atlas whose source lives under github.com/modelcontextprotocol, 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.
- Are modelcontextprotocol's MCP servers and skills safe to install?
- What does this page tell me about modelcontextprotocol?
- Can a publisher change its verdicts?