MCP Rubber Duckofficial
A
licenseA
qualityC
maintenanceAn MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.
12
539 npm
6
MIT
Best Ollama MCP Servers
Ollama is an open-source project that allows you to run large language models (LLMs) locally on your own hardware, providing a way to use AI capabilities privately without sending data to external services.
Why this server?
Allows querying local Ollama models via HTTP.
Why this server?
Supports local Ollama models as the LLM backend for private, on-device generation of cover letters, answers, and command parsing.
MITWhy this server?
Enables agents to probe local GPU/Ollama status, calculate token dollar savings, and route tasks across Luna/Terra/Sol tiers for local model inference.
@nymrel/mcp-hubofficial
AlicenseBqualityBmaintenanceProvides a unified interface for autonomous AI agents to access 14 developer toolchains covering commerce audits, security guards, swarm coordination, machine trust, proof ledgers, crawling, telemetry, pricing, local model routing, micropayments, sandbox isolation, A2UI rendering, and message bus dispatch.14MITWhy this server?
Allows recording and monitoring of local Ollama LLM calls via a wrapped client, capturing trace data for observability.
spanlens-mcpofficial
AlicenseAqualityCmaintenanceMCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).713MITWhy this server?
Provides local summarization of context using an Ollama model.
Why this server?
Allows gut's judgment tools to use local Ollama models via the OpenAI-compatible backend, enabling classify, likely, and rate decisions on locally hosted models.
AlicenseAqualityAmaintenanceJudgment calls on small, fast, cheap models: yes/no, pick-one and rating questions about any text, answered YES, NO or UNSURE. Four tools (likely, classify, rate, each) for TypeSafe's Jev, open models on Ollaya, Ollama or a local NLI model.441,322 PyPI6Apache 2.0Why this server?
Routes local inference through Ollama, automatically selecting and sizing models based on detected VRAM to handle routine coding and QA tasks at zero token cost.
AlicenseAqualityAmaintenanceProvides an MCP endpoint that lets clients like Google Antigravity and Claude Desktop dispatch LLM tasks to local GPU models with automatic hardware-adaptive routing and cloud fallback, enabling near-zero token cost execution.234MITWhy this server?
Allows connecting to a local Ollama server for AI-powered workspace chat and analysis without requiring cloud services.
AlicenseAqualityAmaintenanceThis server enables AI-assisted APK reverse-engineering entirely on-device, orchestrating jadx, apktool, adb, frida, and APKiD through a job/workflow engine, and exposing those agents as native MCP tools for Claude without any cloud dependency.38208MITWhy this server?
Supports local LLMs via Ollama as a backend for free, private inference, useful for classification, formatting, and extraction.
elvatis-mcpofficial
AlicenseBqualityAmaintenanceMCP server for OpenClaw that enables AI clients to control smart home devices, manage memory and cron jobs, and orchestrate multiple AI sub-agents.3752 npmApache 2.0
