"Using llama.cpp and Searxng with local models" matching MCP servers:

Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.

Enables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.

An MCP server that helps interact with and compare different GitHub Models, enabling listing, filtering, and comparing model responses.

MCP server that lists available GitHub Models and compares responses from multiple models for the same prompt.

Enables web search through a LiteLLM proxy's SearXNG-backed search endpoint.

Enables AI coding agents to route tasks to local GPU models via a dynamic heuristic classifier, tracking real-time token dollar savings.

Local-first MCP server for controlling a loopback ComfyUI instance from same-machine or authenticated LAN clients.

Enables running MCP tools against local MLX models on your Mac, with hardware-aware configuration, CLI streaming, and a dashboard for routing and monitoring.

MCP server that delegates mechanical tasks like summarization, classification, extraction, and drafting to a local Llama.cpp LLM, serving as a cost-optimization layer while Claude handles reasoning and quality control.

Exposes locally hosted MLX models as MCP tools for Claude Desktop and Codex, with optional SearXNG search augmentation for private local inference.

Run Liquid AI's LFM2.5 model locally on Mac with a chat UI and MCP server for integration with Claude Desktop, Cursor, and other tools. Offers fast inference, privacy, and multi-Mac clustering.

Enables two local LLMs (Qwen and Llama) to communicate via MCP, allowing one model to consult the other for second opinions or additional reasoning.

Routes code generation tasks between local models and Claude Cloud, optimizing cost by handling simple tasks locally and reserving cloud thinking for complex tasks.

Evaluates task suitability for local models before cloud API calls, routing to Ollama or similar to reduce costs.

Delegates mechanical text-to-text tasks to a local LLM to save Claude subscription quota, reading files server-side so large content never enters Claude's context.

Lets a text-only LLM read images and PDFs by delegating to a vision model running on your own GPU.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.

MCP server connecting Claude Code to LM Studio, delegating token-expensive tasks to a local model while keeping the cloud model in control. It reduces cloud context usage by reading files locally and returning only the processed results.

A fail-closed MCP server for Msty Studio on macOS that provides read-only diagnostics and an optional bounded local-generation tool, without accessing chats, keys, or configuration.