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.
git clone --depth 1 https://github.com/saadmanrafat/uv-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/saadmanrafat/uv-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/saadmanrafat/uv-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/saadmanrafat/uv-mcp/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/saadmanrafat/uv-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/saadmanrafat/uv-mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
uv-mcp 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 3d ago.
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
{
"name": "uv-mcp",
"version": "2.0.0",
"description": "The full uv toolchain for Gemini CLI: projects, dependencies, Python versions, virtual environments, tools, packaging and environment diagnostics.",
"contextFileName": "GEMINI.md",
"mcpServers": {
"uv": {
"command": "uv",
"args": ["run", "--quiet", "--project", "${extensionPath}", "uv-mcp-server"],
"env": {
"UV_MCP_WORKSPACE_ROOT": "${workspacePath}",
"PATH": "${PATH}:${HOME}/.local/bin:${HOME}/.cargo/bin"
}
}
}
}
What ships with it
2 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 17 lines scan A 2b3ad2c1a44a
uv-mcp is a plugin published in the GitHub repository saadmanrafat/uv-mcp (19 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-11-03.
uv-mcp compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uv-mcpsaadmanrafat/uv-mcp | Plugin | 19 | 3d ago | Apache-2.0 | A | — | Gemini CLI |
| python-packageoborchers/fractional-cto | Plugin | 36 | 12d ago | MIT | A | — | Claude Code |
| kernel-sdkskernel/skills | Plugin | 13 | 2d ago | MIT | A | — | Claude Code |
| pykx-knowledgeKxSystems/kx-skills | Plugin | 22 | 22d ago | Apache-2.0 | A | — | Claude Code |
| ida-plugin-developmentHexRaysSA/claude-marketplace | Plugin | 122 | 2mo ago | MIT | A | — | Claude Code |
| pub-pipelinequeelius/claude-anvil | Plugin | 2 | 4d ago | MIT | A | — | Claude Code |
| oat-publish-pythonOpen-Agent-Tools/General-OAT-Skills | Plugin | 3 | 1mo ago | Apache-2.0 | A | — | Claude Code |