Skip to content
Back to search

uptizm

MarketplaceWorks with Claude CodeGitHub

Uptizm for AI agents: the uptizm skill and the Uptizm MCP server.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/uptizm--skills/badge.svg)](/listings/uptizm--skills)

HTML

<a href="/listings/uptizm--skills"><img src="/api/listings/uptizm--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code plugin (skill and MCP server)

/plugin marketplace add uptizm/skills
/plugin install uptizm@uptizm

The plugin adds the skill and the MCP server. Run `/mcp`, pick `plugin:uptizm:uptizm` and sign in with your Uptizm account in the browser. The consent screen asks which team the connection acts on and what it may do: read only, read and write, or full.

Any agent, with the skills CLI

npx skills add uptizm/skills

This installs only the skill. Connect it to your account in one of two ways:

- **MCP**, for any MCP client (Claude Code, ChatGPT, Cursor, Codex, VS Code and more): add the server `https://mcp.uptizm.com` and sign in with your Uptizm account, or send a team API key as its `Authorization` header. In Claude Code: `claude mcp add --transport http uptizm https://mcp.uptizm.com`, then `/mcp`. [Setup for each client](https://uptizm.com/docs/mcp.md). - **API key**, for any agent: create a key in the app under **Settings, Team, API keys** and export it before you start the agent; the skill then uses the REST API.

  export UPTIZM_API_KEY=upz_...

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 26 lines
  1. {
  2. "name": "uptizm",
  3. "description": "Uptizm for AI agents: the uptizm skill and the Uptizm MCP server.",
  4. "owner": {
  5. "name": "Uptizm",
  6. "url": "https://uptizm.com"
  7. },
  8. "plugins": [
  9. {
  10. "name": "uptizm",
  11. "source": "./",
  12. "version": "0.2.0",
  13. "description": "Manage Uptizm monitors, custom metrics, incidents, status pages and boards from Claude Code. Adds the uptizm skill and the remote MCP server at mcp.uptizm.com.",
  14. "homepage": "https://uptizm.com/docs/mcp",
  15. "repository": "https://github.com/uptizm/skills",
  16. "license": "MIT",
  17. "keywords": ["uptime", "monitoring", "incidents", "status-page", "mcp"],
  18. "mcpServers": {
  19. "uptizm": {
  20. "type": "http",
  21. "url": "https://mcp.uptizm.com"
  22. }
  23. }
  24. }
  25. ]
  26. }
README.md · README · 49 lines
  1. # Uptizm skills
  2. Agent skills for [Uptizm](https://uptizm.com), the uptime, incident and status page service. The `uptizm` skill teaches an AI agent to work with your Uptizm team: list monitors and their checks, set up monitoring for a site, add custom metrics, triage incidents, report uptime, build your board, publish status pages and plan maintenance.
  3. The agent uses the [Uptizm MCP server](https://uptizm.com/docs/mcp.md) when it is connected, and the [REST API](https://uptizm.com/docs/quickstart.md) with a team API key otherwise. Both run the same API with the same permissions.
  4. ## Install
  5. ### Claude Code plugin (skill and MCP server)
  6. ```
  7. /plugin marketplace add uptizm/skills
  8. /plugin install uptizm@uptizm
  9. ```
  10. The plugin adds the skill and the MCP server. Run `/mcp`, pick `plugin:uptizm:uptizm` and sign in with your Uptizm account in the browser. The consent screen asks which team the connection acts on and what it may do: read only, read and write, or full.
  11. ### Any agent, with the skills CLI
  12. ```
  13. npx skills add uptizm/skills
  14. ```
  15. This installs only the skill. Connect it to your account in one of two ways:
  16. - **MCP**, for any MCP client (Claude Code, ChatGPT, Cursor, Codex, VS Code and more): add the server `https://mcp.uptizm.com` and sign in with your Uptizm account, or send a team API key as its `Authorization` header. In Claude Code: `claude mcp add --transport http uptizm https://mcp.uptizm.com`, then `/mcp`. [Setup for each client](https://uptizm.com/docs/mcp.md).
  17. - **API key**, for any agent: create a key in the app under **Settings, Team, API keys** and export it before you start the agent; the skill then uses the REST API.
  18. ```
  19. export UPTIZM_API_KEY=upz_...
  20. ```
  21. ## Try it
  22. - "Which of my monitors are down right now?"
  23. - "Monitor https://example.com/health every minute from Europe and the US."
  24. - "Add a metric for the queue backlog in our health endpoint and warn above 100."
  25. - "What happened in last night's incident? Draft a postmortem."
  26. - "What was our uptime over the last 30 days?"
  27. ## How access works
  28. Signing in creates a team API key named after the client, such as "Claude Code (MCP)", when you approve it. You can see and revoke it in **Settings, Team, API keys** like any other key. A key acts on one team only, and each call needs the ability its access level grants; a call it does not cover is refused with the missing ability named. The agent asks you before a call that deletes something or notifies people, such as resolving an incident or announcing maintenance.
  29. ## Documentation
  30. - [Connect an AI agent (MCP)](https://uptizm.com/docs/mcp.md)
  31. - [API quickstart](https://uptizm.com/docs/quickstart.md)
  32. - [Every endpoint](https://uptizm.com/llms.txt)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.