groundcover MCP Server
groundcover publishes a first-party hosted (remote) MCP server that brings live observability data — logs, traces, Kubernetes events, live entity state, monitor issues, monitor definitions and metrics — into an agent's context. It is a query-and-discovery surface: every published tool reads, none write. Most tools take a gcQL pipeline; query_metrics takes PromQL.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport http
Tools
list_workspaces— List the tenants (workspaces) and their backends the authenticated caller can query. Returns tenant_uuid, org_name, tenant_name and backends[]. Call first to discover routing values.query_logs— Run a gcQL query against logs — errors, aggregations, latest message per group.query_traces— Run a gcQL query against trace spans — slow services, 4xx/5xx rates, spans by trace_id.query_events— Run a gcQL query against Kubernetes events — OOMKills, crash loops, scheduling failures.query_entities— Query the live state of tracked entities (Pods, Deployments, Services, Nodes and non-Kubernetes entities). Current snapshot only; ignores start/end/period. The full Kubernetes object surfaces through discoverable raw_json.* paths.query_issues— Run a gcQL query against monitor issue firings.query_metrics— Query metrics with PromQL (four modes).query_monitors— List and filter monitor definitions.search_logs_metadata— Discover log field names and values before writing a gcQL query.search_traces_metadata— Discover trace field names and values.search_events_metadata— Discover Kubernetes event field names and values.search_metrics_metadata— Discover metric names and label values.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.