{"categories":[{"label":"Monitoring","url":"https://skillfed.io/packages/category/system-monitoring/3"}],"enrichment":{"capability":"An MCP server that exposes Grafana dashboards, datasources, and query execution (Prometheus, Loki, ClickHouse, CloudWatch, Elasticsearch, OpenSearch, Snowflake, Athena, InfluxDB, Graphite) to AI clients like Claude Desktop or Cursor.","skillfed_tags":["mcp-server","grafana-integration","ai-assistant"],"use_cases":["Enable Claude or Cursor to search and retrieve Grafana dashboards and extract specific properties without loading full JSON into context.","Allow AI assistants to execute PromQL and LogQL queries against Prometheus and Loki datasources for real-time monitoring insights.","Query ClickHouse, Snowflake, or Athena tables and execute SQL with Grafana macro substitution for data exploration.","Run CloudWatch metric queries and Graphite render API calls from an AI chat interface.","Execute dashboard panel queries with custom time ranges and variable overrides for dynamic analysis.","Retrieve datasource metadata and query examples to help AI assistants learn and construct correct queries."],"what_it_does":"mcp-grafana is a Model Context Protocol server that bridges Grafana and AI clients (Claude Desktop, Cursor, etc.), exposing Grafana's dashboards, datasources, and query capabilities through a standardized protocol. It lets AI assistants search and retrieve dashboards, extract specific dashboard properties via JSONPath, run queries against Prometheus, Loki, ClickHouse, CloudWatch, Elasticsearch, OpenSearch, Snowflake, Athena, InfluxDB, and Graphite datasources, and execute panel queries with custom time ranges and variable overrides.\n\nThe package is designed for integration with MCP-compatible clients rather than direct Python library use. It runs as a standalone server process (typically via uv) and communicates with a Grafana instance using environment variables for authentication (GRAFANA_URL and GRAFANA_SERVICE_ACCOUNT_TOKEN). Several tool groups are disabled by default and must be explicitly enabled via command-line flags. The documentation emphasizes context-window management strategies for large dashboards, recommending summary and property-extraction tools over full dashboard retrieval.","worth_installing":"Yes, if you use Grafana with Claude Desktop, Cursor, or another MCP-compatible AI client and want to query dashboards and datasources conversationally. The package is actively maintained, has no known vulnerabilities, and supports modern Python. Install friction is medium due to platform-specific wheels and the requirement to run as a server process rather than a library, but the setup is straightforward via uv. Not suitable if you need Grafana integration as a Python library for non-MCP applications."},"id":"mcp-grafana","links":{"html":"https://skillfed.io/packages/mcp-grafana","md":"https://skillfed.io/packages/mcp-grafana.md","pypi":"https://pypi.org/project/mcp-grafana/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-10","license_spdx":null,"license_treatment":"permissive","name":"mcp-grafana","python_support":"supports_current","summary":"Grafana MCP server - interact with Grafana via the Model Context Protocol"},"popularity":{"monthly_downloads":678538,"position":5375,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.1.0"}