- Home
- MCP servers
- Gremlin
Gremlin
- typescript
5
GitHub Stars
typescript
Language
6 months ago
First Indexed
2 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": {
"gremlin-mcp": {
"command": "node",
"args": [
"/path/to/gremlin-mcp/build/main.mjs"
],
"env": {
"GREMLIN_API_KEY": "your_gremlin_api_key_here"
}
}
}
}You can interact with Gremlin's reliability management APIs through an MCP server that exposes management, testing, and reporting capabilities. This server lets you view service dependencies, status checks, risks, and reliability analytics, all from your MCP client.
How to use
Connect your MCP client to the Gremlin MCP Server to perform common reliability operations. You can list all RM services, inspect dependencies, pull status checks and risks for services, and generate reliability reports and experiment data. Use the available tool endpoints to query for current state, recent tests, and current test suites. For any operation, supply the required teamId and serviceId when prompted, and include date values in YYYY-MM-DD format where applicable.
How to install
Prerequisites: Node.js 22 or higher, npm, make, and valid Gremlin API credentials.
Step 1: Clone the MCP project and enter the directory.
git clone git@github.com:gremlin/mcp.git gremlin-mcp
cd gremlin-mcp
Step 2: Install dependencies.
make install
Step 3: Build the service.
make
Step 4: Configure your MCP Client. Use the provided example configuration for Claude Desktop to run the service locally.
{
"mcpServers": {
"gremlin_mcp": {
"command": "node",
"args": ["/path/to/gremlin-mcp/build/main.mjs"],
"env": {
"GREMLIN_API_KEY": "your_gremlin_api_key_here"
}
}
}
}
Note: Replace /path/to/gremlin-mcp with the actual path to your service directory.
Configuration notes and security
The MCP server requires a valid Gremlin API key to access reliability APIs. Store the key securely and reference it in your MCP client configuration as shown in the example above.
Troubleshooting
Common issues usually relate to authentication, build status, or incorrect paths in your client configuration. Ensure your API key is valid, the build completed successfully with make, and that the path in your client configuration points to the built main.mjs file.
Tools and endpoints overview
The server exposes several tools to interact with Gremlin reliability data. Below are the available tool endpoints and their purposes.
Available tools
list_services
Lists all reliability management services with descriptions, scores, and targeting information.
get_service_dependencies
Retrieves dependencies for a specific service. Requires teamId and serviceId.
get_service_status_checks
Gets status checks configured for a service. Requires teamId and serviceId.
list_service_risks
Lists identified risks associated with a service. Requires teamId and serviceId.
get_reliability_report
Generates a reliability report for a service on a specific date. Requires teamId, serviceId, and an optional date (YYYY-MM-DD).
get_reliability_experiments
Retrieves recent reliability experiments for a service. Requires teamId and serviceId; optional dependencyId, testId, and limit.
get_recent_reliability_tests
Gets recent reliability tests for a team. Requires teamId; optional pageSize and pageToken.
get_current_test_suite
Retrieves the current test suite for a team or all teams. Optional teamId.