Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/yukakust/joinmultiplayer.ai/gpugit clone --depth 1 https://github.com/yukakust/joinmultiplayer.aiGrade A, and why
gpu scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "gpu": { "url": "https://joinmultiplayer.ai/mcp", "type": "streamable-http" } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 6 lines scan A f7941ccf0c68
gpu is an MCP server published in the GitHub repository yukakust/joinmultiplayer.ai (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
prismaid-mcp
MCP server "prismaid-mcp" as configured in open-and-sustainable/prismaid. Runs in Docker (ghcr.io/open-and-sustainable/prismaid-mcp:0.17.1).
zenodo-mcp
MCP server "zenodo-mcp" as configured in Agostynah/Zenodo-mcp. Runs locally from the zenodo-mcp Python package.
alembica-mcp
MCP server "alembica-mcp" as configured in open-and-sustainable/alembica. Runs in Docker (ghcr.io/open-and-sustainable/alembica-mcp:0.3.5).
zotero-mcp
MCP server "zotero-mcp" as configured in nadavWeisler/zotero-mcp. Runs locally from the nadavweisler-zotero-mcp Python package.
project-bourne
Run reproducible scientific workloads on GPUs, local compute, Slurm, and PBS with provenance. Runs locally from the @project-bourne/mcp npm package.
interpro
InterPro MCP (EBI) — protein family / domain / functional-site classification. Remote server at gateway.pipeworx.io.