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

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.

CNN's Fear & Greed index for the US stock market: current score and rating, the seven component indicators, and about a year of daily history. Go standard library only, no API key required.

Compare service-grant changes, tool alias origins, and saved MCP tool definitions with Gooo rules. Reports preserve incomplete-capture uncertainty and source bindings. No grants are applied and no compared tools are invoked.

Send email, find out why an email failed, set up sending domains, and manage templates, contacts, lists and campaigns in your AhaSend account.

Enables agent tools to validate queries, assess token costs, and extract structured datasets from unstructured text using multiple LLM providers.

MCP server that enables AI assistants to drive systematic literature review workflows, including screening, downloading, converting, and reviewing papers through natural language conversation.

Connects AI tools to GitHub and local git repositories, enabling natural language management of issues, PRs, code analysis, and workflows.

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

Run local AI across all your computers. Toskar's MCP server lets Claude, Cursor, and other clients ask your own local models and search your connected knowledge, with nothing leaving your machines.

A self-hosted MCP server that provides capability packs for AI agents to perform browser, desktop, git, and code actions via schema-validated JSON calls, enabling reliable agentic workflows even with small open-weight models.

An MCP (Model Context Protocol) server for managing Tailscale resources using the official Tailscale Go client library v2. This server provides complete coverage of the Tailscale API with enhanced, self-descriptive tools powered by OpenAPI documentation.

Enables local macOS integration between Apple Reminders and Home Assistant via an MCP server, using EventKit to read and write allowlisted data.

self-hosted development harness (Go engine + CLI + desktop, Linux first) · brief → requirements → spec → plan → build → review → release · verdicts are exit codes, never model opinions · local models first (llama.cpp, vLLM) beside any OpenAI-compatible or Anthropic endpoint · operable by humans or by other agents over MCP with recorded, attributed decisions

An MCP server for fast local source code searching using Zoekt, enabling regex and substring queries across indexed directories.

Provides 23 bounded MCP tools for AI agents to perform technical SEO audits, including crawl setup, page analysis, issue detection, and report exports, all while keeping data local.

Enables AI agents to communicate with business agents across company boundaries using Google's A2A protocol, with tools for discovery, messaging, and connection management.

A self-contained web-research MCP server that lets local LLM agents search, fetch, and synthesize web content using tools like web_search, web_fetch, and web_research.

Enables reading and searching API documentation from YApi instances, allowing AI models to access interface definitions, project API lists, and search through API endpoints using YApi URLs or project IDs.

Model Context Protocol (MCP) server for the Royal Spanish Academy (RAE) API. It allows language models to interact with RAE's dictionary and linguistic resources.

Provides verified, up-to-date model IDs, pricing, and specs for over 100 models across 19 providers, preventing AI agents from using outdated or hallucinated model names.