Exposes Grafana dashboards, alerts, and time-series data to AI agents for reading application health and correlating incidents with code changes. Agents can query metrics, inspect alert rules, and fetch panel data for debugging. Supports Grafana Cloud and self-hosted instances.
Use cases
- SRE correlates application errors with metric spikes during incidents
- Developer investigates slow API responses using dashboard time-series data
- On-call engineer checks alert status and acknowledges active alerts
- Product manager reviews dashboard trends to assess feature performance
- Platform engineer audits alerting rules across multiple Grafana instances
Key features
- Claude Desktop
- Cursor
Frequently Asked Questions
- What Grafana editions are supported?
- Both Grafana OSS (self-hosted) and Grafana Cloud are supported. Cloud requires Grafana Cloud API credentials. OSS requires admin access to configure.
- Can agents modify dashboards or alerts?
- Current implementation is primarily read-only for querying metrics and reading alert states. Dashboard and alert modifications may require separate API access.
- What data sources does it support?
- Any Grafana data source accessible to the authenticated user including Prometheus, Graphite, InfluxDB, Elasticsearch, CloudWatch, Azure Monitor, and more.
Related
Related
3 Indexed items
Datadog MCP Server
Datadog documents a remote Model Context Protocol server at docs.datadoghq.com/bits_ai/mcp_server that connects AI agents in Cursor, Claude Code, Codex CLI, VS Code, Gemini CLI, and other MCP clients to observability data across APM, logs, metrics, monitors, dashboards, and security signals. Setup guides describe OAuth-based connection to Datadog's hosted MCP endpoint (distinct from the local-only Code Security MCP Server used for SAST/SCA scans). Fair-use limits listed in docs include 50 requests per 10 seconds burst and 50,000 monthly tool calls; Audit Trail records MCP actions with tool name, arguments, user identity, and client, while metrics `datadog.mcp.session.starts` and `datadog.mcp.tool.usage` tag usage by client and tool.
LangSmith MCP Server
LangChain documents a LangSmith Model Context Protocol server that lets MCP clients read conversation threads, prompts, runs and traces, datasets, experiments, and billing usage from a LangSmith workspace. For LangSmith Cloud, docs recommend the OAuth-authenticated LangSmith Remote MCP (regional endpoints on api.smith.langchain.com and documented EU/APAC/AWS variants) with the same tool surface and no separate deployment. The standalone HTTP server at https://langsmith-mcp-server.onrender.com/mcp remains documented for API-key access via the LANGSMITH-API-KEY header, while self-hosted LangSmith users can run the open-source langsmith-mcp-server package with uvx, Docker HTTP on port 8000, or point LANGSMITH_ENDPOINT at private instances. Tools include get_thread_history, list_prompts, fetch_runs (with FQL filters and character-budget pagination), dataset/example readers, list_experiments, and get_billing_usage per the official tool table.
Weights & Biases MCP Server
Weights & Biases documents a hosted Model Context Protocol server at `https://mcp.withwandb.com/mcp` (recommended) and an open-source `wandb/wandb-mcp-server` package for local stdio or HTTP per docs.wandb.ai/platform/mcp-server. Authenticated clients pass a W&B API key in the `Authorization: Bearer` header. Documented tools include `query_wandb_tool` and `get_run_history_tool` for experiment metrics, `query_weave_traces_tool` and `count_weave_traces_tool` for LLM traces, `create_wandb_report_tool` for markdown reports, `search_wandb_docs_tool` for docs.wandb.ai, and `query_wandb_entity_projects` for project listings. Dedicated/on-prem deployments can set `WANDB_BASE_URL` with the local server per README.