Steadybit MCP Server
About
Interact with the Steadybit platform to run chaos engineering experiments.
Details
- Author
- steadybit
- Downloads
- 210
- Categories
- Developer Tools, Infrastructure, Other
Jump to
- List experiment designs for a given team
- Retrieve a full experiment design by its key
- Search and filter experiment executions with multiple criteria
- Get details of a specific experiment execution by ID
- List currently registered actions with pagination
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Steadybit MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
You need a Steadybit account and an API token. Set the API_TOKEN environment variable (required) and optionally API_URL (defaults to https://platform.steadybit.com/api). The server can be run via Docker using ghcr.io/steadybit/mcp:latest or built locally from source with Maven and launched directly with Java. Configure it in Claude Desktop under Settings → Developer by adding a JSON entry for the steadybit MCP server.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"steadybit mcp server": {
"mcp-steadybit": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"java",
"-jar",
"target/mcp-1.0.0-SNAPSHOT.jara",
"-e",
"API_URL=https://platform.steadybit.com/api",
"-e",
"API_TOKEN=123456"
]
}
}
}
}McpServers
{
"mcp-steadybit": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"java",
"-jar",
"target/mcp-1.0.0-SNAPSHOT.jara",
"-e",
"API_URL=https://platform.steadybit.com/api",
"-e",
"API_TOKEN=123456"
]
}
}[!WARNING]Deprecated.This standalone MCP server is no longer maintained. Use the hostedRemote MCP Serverthat is built into the Steadybit platform instead — it needs no local installation, supports OAuth, and covers considerably more tools (environments, targets, actions, services, experiment design, suggestions, and run analysis). See thedocumentationfor setup instructions.
MCP server for Steadybit, enabling LLM tools like Claude to interact with the Steadybit platform.
- list-experiment-designs
- List experiment designs
- Required inputs:
- team(string): The team key to list experiment designs for
- Get an experiment design
- Required inputs:
- experimentKey(string): The experiment key to get
- List experiment executions
- Optional inputs:
- experiment(list of string): Filter by one or more experiment keys
- environment(list of string): Filter by one or more environment names
- team(list of string): Filter by one or more team keys
- state(list of string): Filter by one or more result states, possible values are [CREATED, PREPARED, RUNNING, FAILED, CANCELED, COMPLETED, ERRORED]
- from(string, ISO8601 date): Filter by creation date from
- to(string, ISO8601 date): Filter by creation date to
- page(number): Number of the requested page, default is 0
- pageSize(number): Results per page, defaults to 50, maximum 100 is allowed
- Get an experiment execution
- Required inputs:
- executionId(number): The execution id to get
- List of currently registered actions
- Optional inputs:
- page(number): Number of the requested page, default is 0
- pageSize(number): Results per page, defaults to 50, maximum 100 is allowed
- Get a list of environments
- Returns: List of environments
- Get a list of teams
- Returns: List of teams
- Get a list of experiment schedules
- Optional inputs:
- experiment(list of string): Filter by one or more experiment keys
- team(list of string): Filter by one or more team keys
- Get a list of experiment templates (name and ids)
- Get an experiment template including its design
- Required inputs:
- templateId(string): The id of the template to create an experiment from
- Create an experiment from a template
- Needs to be enabled via environment variable, for exampleCAPABILITIES_ENABLED_0=CREATE_EXPERIMENT_FROM_TEMPLATE
- Required inputs:
- templateId(string): The id of the template to create an experiment from
- environment(string): The environment to use for the experiment
- team(string): The team to use for the experiment
- placeholders(object): A map of placeholder keys and their values.
- externalId(string): An optional external id that can be used to update existing experiment designs.
You need a Steadybit account and an API token. You can create an API token in the Steadybit platform underSettings → API Access Tokens. Both token types —AdminorTeam— are supported.
If you want to create experiments, you need a team token for the team you want to create experiments in.
- API_TOKEN: The API token to use for authentication.Required.
- API_URL: The URL of the Steadybit API. Defaults tohttps://platform.steadybit.com/api.
- CAPABILITIES_ENABLED_0,CAPABILITIES_ENABLED_1, ...: Additional capabilities to enable. Currently supported:
- CREATE_EXPERIMENT_FROM_TEMPLATE: Enables thecreate_experiment_from_templatetool.
In Claude Desktop go toSettings → Developer → Editand add the following JSON, replacing<your-api-token>with your actual token:
{ "mcpServers": { "steadybit": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "API_TOKEN", "ghcr.io/steadybit/mcp:latest" ], "env": { "API_TOKEN": "<your-api-token>" } } } }
- Java 21+
- Maven 3.9+
- Docker (only required for the Docker image flow)
- Node.js /npx(used to run the MCP inspector)
The MCP server uses STDIO transport, so there is no console logging. Server output is written tosteadybit-mcp.login the directory where you start the server.
The resulting jar is attarget/mcp-<version>-SNAPSHOT.jar.
npx @modelcontextprotocol/inspector \ java -jar target/mcp-1.0.0-SNAPSHOT.jar \ -e API_URL=https://platform.steadybit.com/api \ -e API_TOKEN=<your-api-token>
Logs are written tosteadybit-mcp.login the directory where you launched the inspector.
Run in Claude Desktop against your local jar
Edit Claude Desktop's developer config (Settings → Developer → Edit) to point at your local Java binary and the freshly-built jar:
{ "mcpServers": { "steadybit": { "command": "/path/to/your/java", "args": [ "-jar", "/path/to/your/.m2/repository/com/steadybit/mcp/1.0.0-SNAPSHOT/mcp-1.0.0-SNAPSHOT.jar" ], "env": { "API_URL": "https://platform.steadybit.com/api", "API_TOKEN": "<your-api-token>", "LOGGING_FILE_NAME": "/path/to/Library/Logs/Claude/steadybit-mcp-server.log" } } } }
- MCP-client logs:~/Library/Logs/Claude/mcp-server-steadybit.log
- MCP-server logs: the path configured viaLOGGING_FILE_NAME(defaults tosteadybit-mcp.lognext to the launcher)
docker build -t steadybit/mcp -f Dockerfile .
Then create aconfig.jsonand run the inspector against the image:
{ "mcpServers": { "steadybit": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "API_TOKEN", "-e", "API_URL", "steadybit/mcp" ], "env": { "API_TOKEN": "<your-api-token>", "API_URL": "https://platform.steadybit.com/api" } } } }
npx @modelcontextprotocol/inspector --config config.json --server steadybit
sdk install java 24.0.1-graalce sdk use java 24.0.1-graalce
Example prompts are inexamples/examples.md.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Aggregates CI failures and outputs GO/NO_GO release verdicts
An MCP server for interacting with the SeaLights platform for quality intelligence.
Enable AI Agents to fix build failures from CircleCI.
Access and interact with Harness platform data, including pipelines, repositories, logs, and artifact registries.
Scout's official MCP pipes error, trace and metric data from production to your AI agent
The Shipyard CLI provides an MCP server for agents to manage Shipyard environments directly: by pulling logs, comparing branches, running tests, and stopping/starting environments..
Generate Playwright BDD tests, GitHub Actions and Azure Pipelines with business-rule traceability, focused CodeGraph context and persistent Engram memory.
AI-powered QA harness that catches JS errors, accessibility failures, visual regressions, and security issues via Chrome DevTools MCP — no test scripts required.
Open-source CLI for testing MCP servers and detecting schema drift
Stateful health monitoring, diagnostics, and web attestation for AI agents. 11 MCP tools. Free Founder's Beta
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
