mcp-grafana
Grafana MCP server - interact with Grafana via the Model Context Protocol
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Grafana 9.0 or later for full functionality.
- Designed to run as an MCP server process, not as a Python library import.
- Medium install friction due to platform-specific wheels, but active maintenance (last commit 2026-08-14, 3356 stars).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions.
last release 2026-08-10 (4 days) · last repo commit 2026-08-14 · 3,356 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 678,538 downloads/mo, #5,375 on PyPI
Alternatives
Verify before relying
# Install via uv (recommended)
uvx mcp-grafana
# Or add to MCP client config (Claude Desktop, Cursor):
# {
# "mcpServers": {
# "grafana": {
# "command": "uvx",
# "args": ["mcp-grafana"],
# "env": {
# "GRAFANA_URL": "http://localhost:3000",
# "GRAFANA_SERVICE_ACCOUNT_TOKEN": "your-token"
# }
# }
# }
# }- Whether datasource-related operations work correctly with Grafana versions earlier than 9.0
- Performance characteristics when querying large dashboards or high-cardinality datasources
- Whether all optional tool groups (runpanelquery, examples, influxdb, etc.) are stable or experimental
What it is and 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.
The 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.
Use it for
- 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.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
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.
Install
mcp-grafana on PyPI
Before you install
Medium install friction due to platform-specific wheels, but active maintenance (last commit 2026-08-14, 3356 stars). Requires Python 3.10+. Designed for integration with uv and MCP clients rather than direct Python use.
Requires Grafana 9.0 or later for full functionality. Designed to run as an MCP server process, not as a Python library import.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions.
Quickstart
# Install via uv (recommended)
uvx mcp-grafana
# Or add to MCP client config (Claude Desktop, Cursor):
# {
# "mcpServers": {
# "grafana": {
# "command": "uvx",
# "args": ["mcp-grafana"],
# "env": {
# "GRAFANA_URL": "http://localhost:3000",
# "GRAFANA_SERVICE_ACCOUNT_TOKEN": "your-token"
# }
# }
# }
# }Verify before relying
- Whether datasource-related operations work correctly with Grafana versions earlier than 9.0
- Performance characteristics when querying large dashboards or high-cardinality datasources
- Whether all optional tool groups (runpanelquery, examples, influxdb, etc.) are stable or experimental
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 4 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 678,538 / month, #5,375 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: mcp_grafana-1.1.0-py3-none-macosx_10_9_x86_64.whl; mcp_grafana-1.1.0-py3-none-macosx_11_0_arm64.whl; mcp_grafana-1.1.0-py3-none-manylinux_2_17_aarch64.whl; mcp_grafana-1.1.0-py3-none-manylinux_2_17_x86_64.whl; mcp_grafana-1.1.0-py3-none-musllinux_1_2_aarch64.whl; mcp_grafana-1.1.0-py3-none-musllinux_1_2_x86_64.whl; mcp_grafana-1.1.0-py3-none-win_amd64.whl; mcp_grafana-1.1.0-py3-none-win_arm64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “grafana mcp server”
- mcp-grafanaAn MCP server that exposes Grafana dashboards, datasources, and query…
- loki-logger-handlerA logging handler that sends Python log messages to Grafana Loki in…
- pyroscope-otelConnects OpenTelemetry tracing with Pyroscope continuous profiling,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Monitoring packages
Wraps any iterable to display a real-time progress bar in the terminal or Jupyter notebook, showing iteration count, elapsed time, and estimated time remaining.
Provides generated Python code for OpenTelemetry semantic conventions, enabling standardized attribute naming and constant definitions for instrumentation and telemetry collection.
Install it if you are using OpenTelemetry and want to follow semantic conventions correctly.
Provides the reference implementation of the OpenTelemetry API for collecting and exporting traces, metrics, and logs from Python applications.
Provides the abstract API and interfaces for OpenTelemetry instrumentation in Python, defining how to emit traces, metrics, and logs without tying code to a specific SDK implementation.
Exports OpenTelemetry observability data to an OpenTelemetry Collector using Protobuf-encoded messages over HTTP.
Install it if you are using OpenTelemetry in Python and need to send data to a Collector over HTTP.
Provides automatic instrumentation commands and programmatic APIs to inject distributed tracing into Python applications without code changes, detecting and instrumenting packages used by your program.
Install it if you need distributed tracing without code changes and have compatible instrumented packages in your environment.
See also awslabs.cloudwatch-mcp-server · grafana-client · grafana-foundation-sdk · grafanalib · snowflake-labs-mcp · blender-mcp · mcp-proxy-for-aws · mcp-clickhouse · loki-logger-handler · locust-plugins