OpsLevel MCP Server
by
Provides AI tools with read‑only access to OpsLevel resources such as actions, campaigns, checks, components, documentation, domains, filters, infrastructure, repositories, systems, teams, and users, enabling conversational agents to retrieve service and infrastructure data.
OpsLevel MCP Server Overview
What is OpsLevel MCP Server about?
The server exposes OpsLevel data through the Model Context Protocol (MCP), allowing AI assistants (Claude, VS Code Copilot, Cursor, Warp, Windsurf, etc.) to query your OpsLevel account without requiring write permissions.
How to use OpsLevel MCP Server?
- Install the binary via Homebrew (
brew install opslevel/tap/opslevel-mcp), Docker (docker pull public.ecr.aws/opslevel/mcp:latest), or download a release from GitHub. - Provide an API token by setting the
OPSLEVEL_API_TOKENenvironment variable. - Configure your AI tool with an MCP server entry that runs
opslevel-mcp(or the Docker command) and passes the token viaenv. - Start the AI application; the server will launch in the background and respond to MCP queries.
Key features of OpsLevel MCP Server
- Read‑only access to a comprehensive list of OpsLevel entities (actions, campaigns, checks, components, docs, domains, filters, infra, repositories, systems, teams, users).
- Multi‑client support with ready‑to‑copy configuration snippets for Claude Desktop, VS Code Copilot, Cursor, Warp, and Windsurf.
- Multiple distribution formats – Homebrew, Docker image, pre‑compiled binaries for macOS, Linux, and Windows.
- Zero‑code setup – only environment variable configuration is required; no additional programming needed.
Use cases of OpsLevel MCP Server
- AI‑driven incident response: let an assistant fetch the latest checks, alerts, or component details while you troubleshoot.
- Documentation lookup: query API or technical docs directly from a chat interface.
- Service catalog exploration: browse domains, systems, and repositories through natural language.
- Team and ownership queries: retrieve who owns a service or component without leaving the AI tool.
- Automation brainstorming: surface existing OpsLevel data to inform pipeline or policy suggestions.
FAQ from the OpsLevel MCP Server
Q: Do I need write permissions for the API token? A: No. The server only performs read‑only operations, so a token with read access to the listed resources is sufficient.
Q: Can I run the server inside Docker?
A: Yes. Pull the image public.ecr.aws/opslevel/mcp:latest and use the Docker command shown in the README for MCP configuration.
Q: Which AI tools are supported? A: Claude Desktop, VS Code Copilot, Cursor, Warp, Windsurf, and any MCP‑compatible client.
Q: How do I update the server?
A: Use the same install method you originally chose (e.g., brew upgrade opslevel-mcp or pull the latest Docker tag).
Q: What happens if my token expires?
A: The server will return authentication errors; refresh the token and update the OPSLEVEL_API_TOKEN environment variable.
OpsLevel MCP Server's README
OpsLevel 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
- Documentation (API & Tech Docs)
- Domains
- Filters
- Infrastructure
- Repositories
- Systems
- Teams
- Users
Setup
- Install the MCP Server
- Homebrew -
brew install opslevel/tap/opslevel-mcp - Docker -
docker pull public.ecr.aws/opslevel/mcp:latest
You can also used a pinned version check out the gallery for the available tags - Manual - Visit our GitHub releases page and download the binary for your operating system.
- Homebrew -
- You will need an API Token to authorize the MCP Server to talk to your account via an environment variable.
- Setup MCP configuration for the AI tool of your choice.
Claude
- Edit the file at the specified path based on the Claude Desktop docs
- Mac OS -
${HOME}/Library/Application\ Support/Claude/claude_desktop_config.json - Windows -
%APPDATA%\Claude\claude_desktop_config.json
- Mac OS -
- Start (or restart) Claude Desktop
{
"mcpServers": {
"opslevel": {
"command": "opslevel-mcp",
"env": {
"OPSLEVEL_API_TOKEN": "XXXXXXX"
}
}
}
}
VS Code
- Open the Settings menu (Command + Comma) and select the correct tab atop the page for your use case
- Workspace - configures the server in the context of your workspace
- User - configures the server in the context of your user
- Select Features → Chat
- Ensure that "Mcp" is Enabled
- You may need to have your Github administrator enable "preview" features in the CoPilot settings for the organization.
- Click "Edit in settings.json" under "Mcp > Discovery" to have the below config
- Can also edit the file directly
- (Mac OS)
${HOME}/Library/Application\\ Support/Code/User/settings.json
- (Mac OS)
- Can also edit the file directly
- Start (or restart) VS Code
{
"chat.agent.enabled": true,
"chat.mcp.discovery.enabled": true,
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "opslevel_token",
"description": "OpsLevel API Token",
"password": true
}
],
"servers": {
"opslevel": {
"type": "stdio",
"command": "opslevel-mcp",
"env": {
"OPSLEVEL_API_TOKEN": "${input:opslevel_token}"
}
}
}
}
}
Cursor
- Open the Cursor menu and select Settings → Cursor Settings → MCP
- Click "Add new global MCP server"
- Add the config below
{
"mcpServers": {
"opslevel": {
"command": "opslevel-mcp",
"env": {
"OPSLEVEL_API_TOKEN": "XXXXXX"
}
}
}
}
Warp
- Access your MCP settings under Settings > AI > Manage MCP Servers. Warp provides instructions for other ways to access this list.
- Press the add button
- Add the config below
{
"opslevel": {
"command": "opslevel-mcp",
"args": [],
"env": {
"OPSLEVEL_API_TOKEN": "XXXXXX"
},
"start_on_launch": true
}
}
Windsurf
- Navigate to Windsurf - Settings > Advanced Settings
- Scroll down to the Cascade section and you will find the option to add a new server
- Edit the mpc_config.json with the below configuration
- 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"
],
OpsLevel MCP Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
OpsLevel MCP Server's Information
- Author
- OpsLevel
- Category
- AI Services
- Language
- Go
- License
- MIT License
- Stars
- 8
- Updated
- about 1 month ago
Related MCP Servers
Discover more MCP servers with similar functionality and use cases
LibreChat
Clientby danny-avila
Provides a customizable ChatGPT‑like web UI that integrates dozens of AI models, agents, code execution, image generation, web search, speech capabilities, and secure multi‑user authentication, all open‑source and ready for self‑hosting.
Blender
by ahujasid
BlenderMCP integrates Blender with Claude AI via the Model Context Protocol (MCP), enabling AI-driven 3D scene creation, modeling, and manipulation. This project allows users to control Blender directly through natural language prompts, streamlining the 3D design workflow.
Pydantic AI
by pydantic
Enables building production‑grade generative AI applications using Pydantic validation, offering a FastAPI‑like developer experience.
Figma
by GLips
Figma-Context-MCP is a Model Context Protocol (MCP) server that provides Figma layout information to AI coding agents. It bridges design and development by enabling AI tools to directly access and interpret Figma design data for more accurate and efficient code generation.
Mcp Use
Clientby mcp-use
Easily create and interact with MCP servers using custom agents, supporting any LLM with tool calling and offering multi‑server, sandboxed, and streaming capabilities.
Talk To Figma
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
WhatsApp MCP Server
by lharries
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp that allows users to search, read, and send WhatsApp messages (including media) through AI models like Claude. It connects directly to your personal WhatsApp account via the WhatsApp web multi-device API and stores messages locally in a SQLite database.
GitMCP
by idosal
GitMCP is a free, open-source remote Model Context Protocol (MCP) server that transforms any GitHub project into a documentation hub, enabling AI tools to access up-to-date documentation and code directly from the source to eliminate "code hallucinations."
Discord
Officialby Klavis-AI
Klavis AI provides open-source Multi-platform Control Protocol (MCP) integrations and a hosted API for AI applications. It simplifies connecting AI to various third-party services by managing secure MCP servers and authentication.