A remote MCP server for Upsun, a platform for hosting and running web applications. It connects an agent to Upsun using an API token, with writing disabled in the shown setup.

For connecting a coding agent to an Upsun account and using Upsun-related tools or information. The input does not specify which individual operations are available.

It gives the agent a way to work with Upsun without manually wiring up a local integration. The provided configuration limits it to non-writing access.

upsun — MCP server for Claude Code and Codex by upsun: A remote MCP server for Upsun, a platform for…

Install

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.

agentmods

npx agentmods add mcp/upsun/ai/upsun-upsun

Clone the repo

git clone --depth 1 https://github.com/upsun/ai

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Or install upsun, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/upsun/ai/upsun-upsun.svg)](https://agentmods.dev/mcp/upsun/ai/upsun-upsun)

Your own site

<a href="https://agentmods.dev/mcp/upsun/ai/upsun-upsun"><img src="https://agentmods.dev/badge/mcp/upsun/ai/upsun-upsun.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

upsun 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 4d 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.

plugins/upsun/.mcp.json · 10 lines

What it actually says

{
  "upsun": {
    "type": "http",
    "url": "https://mcp.upsun.com/mcp",
    "headers": {
      "upsun-api-token": "${UPSUN_API_TOKEN:-}",
      "enable-write": "false"
    }
  }
}

Changes

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.

4d ago First seen · 10 lines scan A 11d65a5e3b46

Subscribe to this mod's changes

upsun is an MCP server published in the GitHub repository upsun/ai (5 stars, last pushed 1mo ago), 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.

Cloud DevOps and cloud

ssh-licco

SSH Model Context Protocol Server - Enable SSH functionality for AI models. Runs locally from the ssh-licco Python package. Needs 4 environment variables to run.

Echoqili/ssh-licco · not measured

tailscale-compute

Run builds, tests, and benchmarks on your own Tailscale compute node. Runs locally from the @dylantirandaz/tailscale-compute-mcp npm package. Needs 6 environment variables to run.

dylantirandaz/tailscale-compute-mcp · not measured

project-bourne

Run reproducible scientific workloads on GPUs, local compute, Slurm, and PBS with provenance. Runs locally from the @project-bourne/mcp npm package.

KozakHou/project-bourne · not measured

playwright

MCP server "playwright" as configured in jtylek/EpesiCRM. Runs C:\Users\jasiek\AppData\Roaming\npm\node_modules\@playwright\mcp\cli.js with node.

jtylek/EpesiCRM · not measured

vllm-ops-mcp

Read-only ops/health MCP server for a local vLLM server (WSL2/systemd-managed): liveness vs real-completion health tiers, GPU/VRAM status, systemd service status, and live serve-flag introspection. No lifecycle-control tools in this release. Runs locally from the vllm-ops-mcp Python package.

jaimenbell/vllm-ops-mcp · not measured

terraform-docs-mcp

MCP server "terraform-docs-mcp" as configured in brightredchilli/terraform-docs. Runs locally from the terraform-docs-mcp Python package.

brightredchilli/terraform-docs · not measured