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

Privacy-respecting web search MCP server for AI assistants using SearXNG, with web search, URL reading, instance failover, and caching.

An MCP server that integrates the SearXNG API for web search and URL content extraction with advanced features like pagination, caching, and proxy support.

An MCP server implementation that integrates the SearxNG API, providing web search capabilities.

Enables privacy-respecting web searches through SearXNG metasearch engine with customizable parameters like language, time range, categories, and engines. Supports safe search levels, pagination control, and basic authentication for secure search operations.

Enables AI assistants to perform web searches and read URL content via a SearXNG instance.

Enables AI assistants to perform privacy-respecting web searches, read URLs, retrieve query suggestions, and inspect search-instance capabilities through the Model Context Protocol.

Free web search for your AI using public SearXNG instances, with parallel multi-server requests and throttling.

Enables clients to list available tools and run searches against a configured SearXNG instance, returning JSON results over either STDIO or HTTP transports.

Enables AI agents to search, read, annotate, and manage a local Zotero library via the Model Context Protocol, with full local storage and no cloud dependency.

Enables agents to perform local metasearch, scholarly and code/model lookups, and fetch rendered web pages or PDFs as paginated markdown, including stealth browsing and arXiv paper overviews.

A local CrossRef database MCP server enabling full-text search across 167M+ scholarly works, citation analysis, and impact factor retrieval without rate limits or internet dependency.

Enables MCP clients to scan local GGUF models, estimate VRAM and suggest GPU offload layers, manage llama-server lifecycle, and proxy OpenAI-format chats with idle auto-unload.

Enables AI clients to preview, search, read, create, update, schedule, and unschedule Garmin Connect workouts using a local Garmin session, with guarded writes and a limited tool set. Supports running, cycling, cardio, and strength workouts without exposing generic API, filesystem, or shell access.

Enables local file reading and writing for your project via Claude Desktop, with tools to read, write, and list files in a specified root path.

Provides Claude and any MCP client with plain-English access to official San Antonio-area public data including weather alerts, school ratings, and 311 service calls, with no API keys required.

Provides AI assistants with plain-English access to official Houston-area public data including weather alerts and school ratings, no API keys required.

A Model Context Protocol server that provides AI assistants with plain-English access to official Dallas-area public data (weather alerts, school ratings, and 311 service requests) without requiring API keys or logins.

Local-first Microsoft Outlook MCP server: a single Go binary that manages calendar events and mail through the Microsoft Graph API over stdio, with tokens stored in the OS keychain and no Entra ID app registration required. Exposes four aggregate tools (calendar, mail, account, system) dispatched by an operation verb, with multi-account support and read-only and mail-gating modes.

Enables AI assistants to answer DFW civic and property questions using official data sources without API keys.

MCP server that delegates Claude Code subagents to alternative backends such as local models, DeepSeek, or AWS Bedrock, while keeping your Claude Code orchestrator session intact.