$ loading_
Explore OpenSearch clusters read-only for logs, indices, and query analysis.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-opensearch" yet — see the docs or source repo.
Connect to the OpenSearch cluster in read-only mode, search error logs from payment-service in the past 24 hours, group them by error type, and list the 10 most representative high-frequency errors.
A summary of error log counts, major exception types, and representative error samples for troubleshooting.
Browse the user-events-* indices in OpenSearch, summarize the number of indices, time range, main fields and field types, and identify key fields suitable for behavior analysis.
An index overview, mapping summary, and recommended key fields for further analysis.
Run a query in OpenSearch to calculate daily API request volume over the last 7 days and show the trend of 5xx response rate.
Daily aggregated request counts, 5xx rate trends, and a brief readable analysis.
Search, aggregate, and explore OpenSearch logs and index metadata read-only.
Retrieve error stack traces from OpenSearch logs by transaction ID.
Let LLMs read dashboard objects and query logs via OpenSearch Dashboards.
Inspect Kubernetes resources, pod details, and logs for safe troubleshooting.
Expose OpenAPI endpoints as MCP tools for LLM-driven REST API access.
Securely interact with Elasticsearch for search, data management, and exports.