OpsLevel MCP Server

[!WARNING] This self-hosted MCP server is deprecated. New users should prefer the hosted MCP server at https://app.opslevel.com/mcp, which requires no local install or binary management and stays automatically up to date.

Using the hosted MCP server

The hosted server uses OAuth — no API token, binary, or client secret to manage. For any AI tool that supports remote MCP servers, the only value you need to configure is the URL:

config.json

Copy

{
    "mcpServers": {
        "opslevel": {
            "url": "https://app.opslevel.com/mcp"
        }
    }
}

Your client discovers the OAuth configuration automatically and opens a browser for you to log in to OpsLevel and grant access. Notes:

• Authentication is OAuth 2.1 (Dynamic Client Registration + authorization code with PKCE) — your MCP client handles this for you, including refreshing the short-lived access tokens.
• The transport is streamable HTTP (not SSE). If your client asks, choose the HTTP / streamable-HTTP option.
• Consult your AI tool's documentation for exactly where to add a remote MCP server.

This MCP (Model Context Protocol) server provides AIs with tools to interact with your OpsLevel account.

Features

Currently, the MCP server only uses read-only access to your OpsLevel account and can read data from the following resources:

• Actions
• Campaigns
• Checks
• Components
• Component Dependencies (components that a component depends on)
• Component Dependents (components that depend on a component)
• Documentation (API & Tech Docs)
• Domains
• Filters
• Infrastructure
• Repositories
• Systems
• Teams
• Users

Setup

1. Install the MCP Server
   1. Homebrew - brew install opslevel/tap/opslevel-mcp
   2. Docker - docker pull public.ecr.aws/opslevel/mcp:latest
      You can also used a pinned version check out the gallery for the available tags
   3. Manual - Visit our GitHub releases page and download the binary for your operating system.
2. You will need an API Token to authorize the MCP Server to talk to your account via an environment variable.
3. Setup MCP configuration for the AI tool of your choice.

Claude

Claude Desktop

1. Edit the file at the specified path based on the Claude Desktop docs
   1. Mac OS - ${HOME}/Library/Application\ Support/Claude/claude_desktop_config.json
   2. Windows - %APPDATA%\Claude\claude_desktop_config.json
2. Start (or restart) Claude Desktop

{
    "mcpServers": {
        "opslevel": {
            "command": "opslevel-mcp",
            "env": {
                "OPSLEVEL_API_TOKEN": "XXXXXXX"
            }
        }
    }
}

VS Code

VS Code User Settings

1. Open the Settings menu (Command + Comma) and select the correct tab atop the page for your use case
   1. Workspace - configures the server in the context of your workspace
   2. User - configures the server in the context of your user
2. Select Features → Chat
3. Ensure that "Mcp" is Enabled
   1. You may need to have your Github administrator enable "preview" features in the CoPilot settings for the organization.
4. Click "Edit in settings.json" under "Mcp > Discovery" to have the below config
   1. Can also edit the file directly
      1. (Mac OS) ${HOME}/Library/Application\\ Support/Code/User/settings.json
5. Start (or restart) VS Code

{
    "chat.agent.enabled": true,
    "chat.mcp.discovery.enabled": true,
    "mcp": {
        "inputs": [
          {
            "type": "promptString",
            "id": "opslevel_token",
            "description": "OpsLevel API Token",
            "password": true
          }
        ],
        "servers": {
            "opslevel": {
                "type": "stdio",
                "command": "opslevel-mcp",
                "env": {
                    "OPSLEVEL_API_TOKEN": "${input:opslevel_token}"
                }
            }
        }
    }
}

Cursor

Cursor Docs

1. Open the Cursor menu and select Settings → Cursor Settings → MCP
2. Click "Add new global MCP server"
3. Add the config below

{
  "mcpServers": {
    "opslevel": {
      "command": "opslevel-mcp",  
      "env": {
        "OPSLEVEL_API_TOKEN": "XXXXXX"
      }
    }
  }
}

Warp

Warp

1. Access your MCP settings under Settings > AI > Manage MCP Servers. Warp provides instructions for other ways to access this list.
2. Press the add button
3. Add the config below

{
  "opslevel": {
    "command": "opslevel-mcp",
    "args": [],
    "env": {
      "OPSLEVEL_API_TOKEN": "XXXXXX"
    },
    "start_on_launch": true
  }
}

Windsurf

Windsurf

1. Navigate to Windsurf - Settings > Advanced Settings
2. Scroll down to the Cascade section and you will find the option to add a new server
3. Edit the mpc_config.json with the below configuration
4. Restart Windsurf

{
  "mcpServers": {
    "opslevel": {
      "command": "opslevel-mcp",  
      "env": {
        "OPSLEVEL_API_TOKEN": "XXXXXX"
      }
    }
  }
}

Docker

If you didn't install the binary directly and instead pulled the docker image you'll need to adjust the above MCP configurations to support running the server via docker

        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "OPSLEVEL_API_TOKEN",
          "public.ecr.aws/opslevel/mcp:latest"
        ],