"Local RAG system for providing documentation to a large language model (LLM)" matching MCP servers:

Runs a language server and provides tools for communicating with it. Language servers excel at tasks that LLMs often struggle with, such as precisely understanding types, understanding relationships, and providing accurate symbol references.

Read-only MCP server for observing Linux hosts (systemd, ZFS, Docker, VMs, network, hardware, NixOS) as a graph of objects with provenance. Provides seven tools to list hosts, get status, collections, objects, evidence, lookup, and changes.

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up-to-date model IDs, pricing, and specs for over 100 models across 19 providers, preventing AI agents from using outdated or hallucinated model names.

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.

LLM Optimizer is an AI visibility intelligence platform. It analyzes how large language models and AI search engines perceive, cite, and recommend brands; then provides research-backed optimization strategies to improve that visibility.

AI modifies a function but misses 5 callers that also need updating. crag fixes this — it builds precise call graphs via static analysis, so AI knows exactly what's affected before making changes.

Local MCP server for asynchronous coding-agent delegation, enabling Claude Code or Codex to delegate tasks to Cursor, Pi, Codex, or Claude Code and collect results later.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around. MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.

Connect AI agents like Claude, Cursor, and Gemini to historical Windows performance and privacy data gathered by the AppControl Windows app. This server enables natural language queries into CPU, GPU, and temperature history alongside system security events for deep local auditing.

MCP server that integrates with VictoriaMetrics vmanomaly API to enable AI-assisted anomaly detection, model management, and configuration generation.

Connect to your TTRPG campaign's repository and database. Instead of retrieving prose, its 48 tools (20 read, 28 write) return typed state: 14 entity schemas (NPCs, factions, locations, sessions, lore), relationship and knowledge-graph queries, wiki blocks, and a narrative-state bundle of open threads and canon facts.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

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

Open source MCP server specializing in easy, fast, and secure tools for Databases.

See which process holds a local port and who started it, find free ports, wait for services, and stop a dev server safely. Fixes "port already in use" (EADDRINUSE) for AI coding assistants. Never stops system processes; Docker and WSL ports get the right stop command. Run with: npx -y portcheck-cli mcp

Local-first Git hosting for AI coding agents. lgh serve turns any directory into an HTTP Git remote (127.0.0.1:9418) with push events, commit-status reporting, smart .gitignore generation, secret/large-file detection, and optional LAN sharing with auth. The MCP server exposes 10 tools covering repo registration, one-command backup (lgh up), server control, and event access.

Local-first MCP server providing semantic search over library docs, fully offline. Single Go binary speaks MCP over stdio against a vector index pinned to the binary version. Like Context7 with the internet turned off. Apache 2.0. Linux + macOS, also available as a container image.

A local AST and type-aware Go repository context indexer that uses CHA to map symbols, call graphs, dependencies, and architecture patterns. Built for AI coding agents that need to navigate and reason about large Go codebases without reading raw files.

Local, open-source multi-account MCP broker — one endpoint, every account. Add credentials once and switch identity without reconnecting, from any LLM client.