by steadybit
Enables LLM tools to interact with the Steadybit platform, providing operations such as listing experiments, retrieving designs, managing executions, and more.
Enables large‑language‑model tools to query and manipulate Steadybit experiment data via a standard Model Context Protocol (MCP) server. The server exposes a set of tools that retrieve experiment designs, executions, actions, environments, teams, schedules, and templates, and optionally create new experiments from templates.
API_TOKEN (the token)API_URL (default: https://platform.steadybit.com/api)CAPABILITIES_ENABLED_* to enable extra capabilities such as CREATE_EXPERIMENT_FROM_TEMPLATE.docker run -i --rm -e API_TOKEN -e API_URL steadybit/mcp
list-experiment-designs, get_experiment_execution, list_actions, etc., providing the required inputs.steadybit-mcp.log to keep STDIO clean for MCP communication.Q: Which token types are supported?
A: Both Admin and Team tokens work. Use a team token if you need to create experiments in a specific team.
Q: How do I enable creating experiments from templates?
A: Set an environment variable like CAPABILITIES_ENABLED_0=CREATE_EXPERIMENT_FROM_TEMPLATE before starting the server.
Q: Where can I find the server logs?
A: Logs are written to steadybit-mcp.log in the working directory, or to a custom path defined by LOGGING_FILE_NAME.
Q: Is there a native binary available?
A: Yes. Build it with GraalVM using the -Pnative Maven profile (mvn -Pnative native:compile).
Q: Can I run the server locally without Docker?
A: Absolutely. After mvn clean install, run the JAR: java -jar target/mcp-1.0.0-SNAPSHOT.jar with the required environment variables.
MCP Server for Steadybit, enabling LLM tools like Claude to interact with the Steadybit platform.
list-experiment-designs
team (string): The team key to list experiment designs forget_experiment_design
experimentKey (string): The experiment key to getlist_experiment_executions
experiment (list of string): Filter by one or more experiment keysenvironment (list of string): Filter by one or more environment namesteam (list of string): Filter by one or more team keysstate (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 fromto (string, ISO8601 date): Filter by creation date topage (number): Number of the requested page, default is 0pageSize (number): Results per page, defaults to 50, maximum 100 is allowedget_experiment_execution
executionId (number): The execution id to getlist_actions
page (number): Number of the requested page, default is 0pageSize (number): Results per page, defaults to 50, maximum 100 is allowedlist_environments
list_teams
list_experiment_schedules
experiment (list of string): Filter by one or more experiment keysteam (list of string): Filter by one or more team keyslist_experiment_templates
get_experiment_template
templateId (string): The id of the template to create an experiment fromcreate_experiment_from_template
CAPABILITIES_ENABLED_0=CREATE_EXPERIMENT_FROM_TEMPLATEtemplateId (string): The id of the template to create an experiment fromenvironment (string): The environment to use for the experimentteam (string): The team to use for the experimentplaceholders (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 to have a Steadybit account and an API token. You can create an API token in the Steadybit platform under
"Settings" → "API Access Tokens". Both token types, Admin or Team 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. This is required.API_URL: The URL of the Steadybit API. Default is https://platform.steadybit.com/api.CAPABILITIES_ENABLED_0,CAPABILITIES_ENABLED_1,...: A comma-separated list of additional capabilities to enable.
The capabilities are:
CREATE_EXPERIMENT_FROM_TEMPLATE: Enables the create_experiment_from_template tool.<your-api-token> with your actual API token.:
{
"mcpServers": {
"steadybit": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"API_TOKEN",
"ghcr.io/steadybit/mcp:latest"
],
"env": {
"API_TOKEN": "<your-api-token>"
}
}
}
}
Please note that there will be no logging to the console when running the MCP Server. The server uses STDIO transport
to communicate with the MCP Clients. Have a look at the steadybit-mcp.log file to see the output of the server.
Build the project:
mvn clean install
Test with the MCP inspector:
npx @modelcontextprotocol/inspector java -jar target/mcp-1.0.0-SNAPSHOT.jara -e API_URL=https://platform.steadybit.com/api -e API_TOKEN=123456
steadybit-mcp.log located in the folder where you started the inspector.Use in Claude Desktop
{
"mcpServers": {
"steadybit": {
"command": "/Users/danielreuter/.sdkman/candidates/java/current/bin/java",
"args": [
"-jar",
"/Users/danielreuter/.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": "123456",
"LOGGING_FILE_NAME": "/Users/danielreuter/Library/Logs/Claude/steadybit-mcp-server.log"
}
}
}
}
~/Library/Logs/Claude/mcp-server-steadybit.log~/Library/Logs/Claude/steadybit-mcp.log, depending on the LOGGING_FILE_NAME
you set in the env section.Build the image:
docker build -t steadybit/mcp -f Dockerfile .
Create a file config.json with the following content:
{
"mcpServers": {
"steadybit": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"API_TOKEN",
"-e",
"API_URL",
"steadybit/mcp"
],
"env": {
"API_TOKEN": "123456",
"API_URL":"https://platform.steadybit.com/api"
}
}
}
}
Run the inspector:
npx @modelcontextprotocol/inspector --config config.json --server steadybit
Install GraalVM 24.0.1 with the following command using sdkman:
sdk install java 24.0.1-graalce
Use the GraalVM version:
sdk use java 24.0.1-graalce
Build the native image:
mvn -Pnative native:compile
You can find some example prompts here.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by modelcontextprotocol
An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.
by danny-avila
Provides a self‑hosted ChatGPT‑style interface supporting numerous AI models, agents, code interpreter, image generation, multimodal interactions, and secure multi‑user authentication.
by block
Automates engineering tasks on local machines, executing code, building projects, debugging, orchestrating workflows, and interacting with external APIs using any LLM.
by RooCodeInc
Provides an autonomous AI coding partner inside the editor that can understand natural language, manipulate files, run commands, browse the web, and be customized via modes and instructions.
by pydantic
A Python framework that enables seamless integration of Pydantic validation with large language models, providing type‑safe agent construction, dependency injection, and structured output handling.
by lastmile-ai
Build effective agents using Model Context Protocol and simple, composable workflow patterns.
by mcp-use
A Python SDK that simplifies interaction with MCP servers and enables developers to create custom agents with tool‑calling capabilities.
by nanbingxyz
A cross‑platform desktop AI assistant that connects to major LLM providers, supports a local knowledge base, and enables tool integration via MCP servers.
by gptme
Provides a personal AI assistant that runs directly in the terminal, capable of executing code, manipulating files, browsing the web, using vision, and interfacing with various LLM providers.