"Supabase (open source Firebase alternative)" matching MCP servers:

Enables AI agents to browse and filter experiment runs, retrieve metrics, logs, tables, and artifacts, plot comparisons as PNG images, and download full-fidelity training history for local analysis against a self-hosted Open Train server. It also provides diagnostic tooling that surfaces metric evidence and investigation leads without asserting causality.

Multi-machine system monitor with a built-in MCP server that enables AI agents to query health metrics, manage processes, schedule cron jobs, and run diagnostics across local and remote machines.

Radar is an open-source Kubernetes observability and diagnostics MCP server. It exposes cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions to AI agents through the Model Context Protocol.

Open-source .NET framework and server for Model Context Protocol (MCP) with enterprise OAuth 2.0/OIDC auth, per-tool MFA, OpenTelemetry, and health checks.

MCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).

Open-source MCP server for Umami Analytics — Cloud and self-hosted.

Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read-only, plus 8 write tools gated behind --allow-write); source lives in the datanika-mcp/ subdirectory of the repo.

An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.

Open-source MCP gateway connecting AI agents like Claude Desktop and Claude Code to SuiteCRM. 24 CRM tools over SSE with OAuth2/OIDC auth, multi-entity support, ACL enforcement, and Prometheus/Grafana observability.

An open source MCP server empowering SREs with intelligent observability, predictive analytics, and AI-driven automation across Kubernetes, OpenShift, and Tekton environments.

Kubernetes MCP server built into Sextant, a free open-source desktop client: agents get per-cluster permissions (off by default), every change needs a confirmation in the window, and every call is logged. Tools cover resources, logs, events, metrics, scale, restart, Helm, Flux and Argo CD.

An open-source, vendor-agnostic MCP governance proxy that sits between AI clients and tool servers to apply response projection, metering, and retry policies, reducing token bloat and providing per-tool cost visibility.

An MCP server that enables AI agents to safely operate multi-cluster Kubernetes fleets through an Open Cluster Management hub, with policy enforcement, human approval, and audit tracing.

agent-bom is an open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. The default scan profile in MCP server mode exposes 8 MCP tools. Additional profiles provide inventory, findings, compliance, graph, and runtime workflows. See the published Glama release for its packaged version.

iOS leak hunting and performance investigation. Reads .memgraph and .trace files, classifies retain cycles against a 34-pattern catalog with Swift fix templates, bridges to source via SourceKit-LSP. 28 MCP tools, 34 catalog resources, 5 investigation prompts.

AI-powered threat intelligence server with real-time alert monitoring and multi-source IOC analysis, enabling security investigations directly in Claude Desktop.

Enables real-time monitoring of F5 Cloud service status, including 148+ service components, active incidents, and scheduled maintenance windows with intelligent caching and dual data source reliability.

Exposes Modal cloud functions as MCP tools for video rendering, voice synthesis, and app management. Enables LLM agents to execute Remotion renders, F5-TTS voice cloning, and monitor Modal applications via Supabase-backed infrastructure.

Security-focused MCP server for TP-Link Omada Open API workflows, enabling network management via natural language.

Enables coding agents to read a replay link or a gn-tracing-*.zip package, surfacing console errors with source-mapped stacks, failed requests, and the user timeline.