"ollama" matching MCP servers:

An MCP server for autonomous Kubernetes troubleshooting and remediation. It enables continuous cluster monitoring, local AI-powered diagnosis via Ollama, and automated kubectl-based fixes.

Enables causal root cause analysis with 56 tools covering causal graph construction, 10 RCA model families plus 3 dedicated PyRCA algorithms (Salesforce PyRCA, BSD-3-Clause), multi-model consensus, and PDF/HTML/Excel/Markdown report generation. Works with Claude, Ollama, Groq, OpenAI, Gemini, LangChain, Cursor — 10 providers.

Enables observability and governance for local LLMs via Ollama, including auditing model usage, scanning prompts for secrets/PII, and enforcing allow/deny policies.

Enables MCP clients to interact with a local AI agent through Ollama, providing tools for checking weather, current time, and available models, while tracing calls to Langfuse.

Enables agents to query real-time and historical metrics for locally served Ollama and vLLM instances, including request rates, latency, token counts, and GPU utilization, over stdio.

A high-performance control plane for Ollama-based local LLM sessions with background memory consolidation, hybrid cloud planning, and real-time fleet monitoring.

Unified local MCP AI Gateway that routes across Groq, OpenRouter, Mistral, and local Ollama providers, with OpenAI-compatible APIs, MCP tools, fallback/racing router, monitoring, and web dashboard.