hny-mcp
Honeycomb MCP Server
A Model Context Protocol server for interacting with Honeycomb observability data. This server enables LLMs like Claude to directly analyze and query your Honeycomb datasets across multiple environments.
Features
- Query Honeycomb datasets across multiple environments
- Analyze columns and data patterns
- Run basic analytics queries
- Monitor SLOs and their status
- View and analyze Triggers
- Access dataset metadata and schema information
Installation
Configuration
Create a configuration file at ~/.hny/config.json
with your Honeycomb environments and API keys:
Each environment entry can also optionally include a baseUrl
if you're using a different API endpoint.
Usage
With Claude Desktop
Add this to your Claude Desktop configuration (claude_desktop_config.json
):
Available Tools
list-datasets
: List all datasets in an environmentget-columns
: List all columns in a datasetrun-query
: Run basic analytics queries with aggregationsanalyze-column
: Get detailed analysis of specific columnslist-slos
: View all SLOs for a datasetget-slo
: Get detailed SLO status including compliancelist-triggers
: View all triggers for a datasetget-trigger
: Get detailed trigger information
Resources
The server exposes Honeycomb datasets as resources with the URI format:
honeycomb://{environment}/{dataset-slug}
For example:
honeycomb://production/api-requests
honeycomb://staging/backend-services
Development
Requirements
- Node.js 16+
- Honeycomb API keys with appropriate permissions:
- Query access for analytics
- Read access for SLOs and Triggers
- Environment-level access for dataset operations
Example Queries
Ask Claude things like:
- "What datasets are available in the production environment?"
- "Show me the SLO compliance for the API availability in production"
- "Are there any active triggers in the staging environment?"
- "What's the error rate in the production API dataset over the last hour?"
License
MIT
Server for interacting with Honeycomb observability data. This server enables LLMs like Claude to directly analyze and query your Honeycomb datasets.