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

MCP server for local web search via SearXNG, providing unlimited queries without API keys or cost, with automatic fallback to public instances.

Enables Claude Code to query locally hosted Qwen models on Apple Silicon Macs for drafting, translating, summarizing, or a second opinion, with an optional deeper-thinking mode for harder problems.

A minimal MCP server that exposes a run_command tool over stdio, enabling command execution within a Docker container.

An MCP server for SearXNG that provides LLM agents with advanced search tools, including engine and category targeting, multi-page fanout, and dynamic descriptions from the live engine pool.

MCP server for private web search via self-hosted SearXNG with local reranking, full-page content fetching via Firecrawl, and optional Ollama-powered query expansion and summaries.

Turns product ideas into rendered UI screen mockups and a buildable component manifest, so downstream agents can develop real screens from the generated designs.

Adds web search to Claude Desktop through a user-selected SearXNG instance, with engine and category selection, language and time-range filters, and bounded result counts.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

An MCP server that wraps a local SearXNG instance to provide private, customizable web search capabilities. It enables AI assistants to perform queries with support for specific parameters like results limits, language, and time ranges.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

Enables fetching weather forecasts for the USA via NWS API and for Israel via browser automation using Playwright.

Enables web search and content scraping from multiple engines via a local SearXNG instance, allowing AI assistants to retrieve and extract web content.

Self-hosted SearXNG metasearch for MCP clients: web, image, news, video, music and page fetch.

This server provides a privacy-focused meta search capability by integrating multiple search engines without tracking or user profiling, supporting various categories and languages for filtered searches.

An MCP server for managing SearXNG instances, enabling configuration inspection, engine toggling, health checks, and container lifecycle control.

Implements a secure MCP server with API Key and JWT authentication, providing tools like echo, login, secure_action, and admin_action. Includes MCP Inspector integration for testing and debugging.

Enables chat-driven audio analysis and enhancement using local Claude, including denoising, EQ, compression, and loudness normalization, with an A/B viewer for synchronized comparison.

Enables downloading, configuring, benchmarking, starting, and stopping local GGUF llama.cpp model profiles through MCP tools, while exposing an OpenAI-compatible API for using the running models.

Enables local LLMs in LM Studio to perform web searches through a privacy-focused local SearXNG instance. It features concurrent search capabilities, automatic result caching, and advanced filtering options like domain exclusion and time-range limits.

Gives coding agents a single search tool backed by a self-hosted SearXNG instance, parsing and scrubbing queries, merging duplicates, and ranking results with BM25F plus optional decision-model reranking. Returns compact, token-efficient results with relevance bands, engine warnings, and optional stop/refine/broaden hints.