- Home
- MCP servers
- Statsig
Statsig
- python
0
GitHub Stars
python
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"geli2001-statsig-mcp": {
"command": "uv",
"args": [
"run",
"-m",
"statsig_mcp",
"--api-key",
"console-xxx",
"--environment",
"production",
"--api-timeout",
"5000",
"--debug"
],
"env": {
"STATSIG_DEBUG": "true",
"STATSIG_API_TIMEOUT": "5000",
"STATSIG_ENVIRONMENT": "production",
"STATSIG_CONSOLE_API_KEY": "console-xxx",
"STATSIG_DISABLE_LOGGING": "false"
}
}
}
}You can run the Statsig MCP Server locally to manage feature gates, dynamic configs, experiments, segments, and other platform administration tasks through an MCP client. This server lets your AI assistants interact with Statsig’s Console API for complete feature management and observability, making it easier to automate and test experiments and configurations.
How to use
You will run the MCP server in a local environment and connect your MCP client to it. Start the server with your preferred runtime and provide the Console API key you obtained from Statsig. You can run the server using uv for quick setup or with Python directly. Once running, you can perform operations like listing and managing feature gates, dynamic configs, experiments, segments, metrics, audit logs, target apps, API keys, and team members. You can also query available event types for your project.
How to install
Prerequisites: you need Python 3.10+ and a runtime to execute MCP commands (uv is recommended). Prepare your environment and then install the MCP package in development or production mode as described.
# Install in development mode with dev dependencies
pip install -e ".[dev]"
# Run tests or start the server after installation
uv run -m statsig_mcp --api-key "console-xxx" --environment production --debug
Other important notes
Configuration and runtime options are exposed as command-line arguments or environment variables. You can control the environment, API timeouts, and debugging output to suit development or production use cases. When sharing keys, use separate API keys for different environments and never expose your Console API key in client-side code.
Available tools
check_feature_gate
Check whether a specific feature gate is enabled for a given user and context.
get_dynamic_config
Retrieve the dynamic config value for a user or context.
log_event
Log a custom event directly to Statsig with metadata and user attributes.
query_events
List all configured event types in your Statsig project.
get_user_by_email
Retrieve team member information by email address.
list_team_users
List all team members in your Statsig project.
list_gates
List all feature gates in the project.
get_gate
Get details for a specific feature gate.
create_gate
Create a new feature gate.
update_gate
Update an existing feature gate.
delete_gate
Delete a feature gate.
list_experiments
List all experiments.
get_experiment
Get details of a specific experiment.
create_experiment
Create a new experiment.
update_experiment
Update an existing experiment.
delete_experiment
Delete an experiment.
list_dynamic_configs
List all dynamic configs.
get_dynamic_config
Get details of a specific dynamic config.
create_dynamic_config
Create a new dynamic config.
update_dynamic_config
Update an existing dynamic config.
delete_dynamic_config
Delete a dynamic config.
list_segments
List all segments.
get_segment
Get details of a specific segment.
create_segment
Create a new segment.
list_target_apps
List all target apps.
get_target_app
Get details of a specific target app.
list_api_keys
List all API keys.