One-file Windows MCP workspace server with Secure MCP Tunnel integration, encrypted credentials, GUI controls, and automatic tunnel startup.

Local documentation search for AI assistants, from Git repos and local directories

Deterministic local code context for coding agents.

MCP server for accessing VS Code/Cursor Local History

Encrypted, offline long-term memory for AI agents via MCP.

Run, fit, and route work to local LLMs: one MCP server for Ollama, LM Studio, llama.cpp, Docker Model Runner, MLX, vLLM, and Foundry Local, with hardware-aware model selection.

MCP server for WordPress database access via Local by Flywheel

—

Local documentation search for AI assistants, from Git repos and local directories

Local, API-key-free mem0 long-term memory for Claude Code (and any MCP client)

MCP server for delegating mechanical tasks to local LLMs via Ollama

Local MCP server and CLI for the Local SEO extension: Google Business Profile and Maps audits.

MCP server enabling AI agents to search across local media sources with MCP-compatible client integration

Local stdio MCP Server for Jina AI - Web search, reading, academic search, and more

Delegate mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscription quota.

A not-so-useful local MCP server.

AI model router for agents. Checks whether a local model can handle the task before calling cloud inference. LOCAL/CLOUD verdict saves cost on every call.

Transcribe meetings, calls and dictation locally on your Mac – with speaker recognition, no cloud. Whisper + pyannote, menu bar app. German and English.

A lightweight, extensible Model Context Protocol (MCP) server for secure key management in local AI agents

Fully local semantic memory for AI agents over MCP — Ollama embeddings, nothing leaves your machine

MCP server for local LLM inference on Ryzen AI Max+ 395 with queueing, deadlines and telemetry; benchmark findings

Local-only MCP proxy for sharing Mobbin and Refero across local AI clients.

Free MCP LOCAL [Good Work !]

Local-first MCP bridge between coding agents and a Figma Desktop development plugin

MCP server for delegating mechanical tasks to local LLMs via Ollama. Claude does the thinking, your local model does the grunt work.

Local RAG MCP Server with extended file support (including PPTX)

MCP "server" that can perform a web search locally without the use of APIs.

MCP server for accessing VS Code/Cursor's Local History

Offline terminal, browser, and web-search tools for any local LM Studio model — no cloud API, no API keys.

MCP server for Glean API integration

Local multimodal inference service

Local-first realtime web research MCP for LM Studio. No API keys, clickable citations.

Comprehensive toolkit & Web dashboard for Factorio 2.1+ (Space Age) mod localization, missing key scanning, syntax validation, and quality auditing.

Local Growth Crew by Modern Mustard Seed: a Claude plugin with four agents, seven skills and five free MCP servers that audit and grow a local business online.

Local-first CRM built on the Model Context Protocol (MCP) — customer/project management exposed as MCP tools, usable from a custom LlamaIndex agent or directly in Claude Code or any other applications supporting MCP Servers or resources.

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

Local RAG MCP Server - Enhanced with hybrid search, memory management, and code file support (fork of shinpr/mcp-local-rag)

MCP server for fast local Lean and Mathlib theorem search with tree-sitter indexing and proof probes

Local RAG MCP Server - Easy-to-setup document search with minimal configuration

Fully local semantic memory for AI agents: search your notes and session logs from any MCP client, with embeddings served by Ollama

!!! vibe-coded !!! Read-only MCP server for secure access to local project files.

Local MCP server for UI component generation - no API key required

MCP server with FAISS local vector database for RAG

Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.

Read-only MCP server for semantic search over a local document corpus — on-device embeddings (Ollama), local Chroma store, symlink-hardened file access. Sibling of claude-code-session-memory.

Local RAG MCP Server for opencode - with automatic MCP instructions for project/common indexing

MCP server — one-shot install + query for memos (PostgreSQL) and memuK (SQLite) local memory. Designed for OpenClaw agents.

Run local MCP for hexdocs digest, hex-search, gh-search, remember and recall learnings

MCP memory service for llama-server

Project-isolated local knowledge and persistent memory gateway for Codex, Cursor, and Antigravity via MCP

This is a local rag with retrieval-augmented experience log for coding with indexed framework, reranking documents, emdedding-normalization

Local-first, cognitive persistent memory & knowledge graph for AI coding agents via Model Context Protocol (MCP)

Local-first long-term memory for AI agents. SQLite, offline, zero cloud. MCP server.

Community archive of mingrath/chatgpt-sol-local-bridge, a cross-platform local MCP bridge for ChatGPT.

Local Process Intelligence MCP-Server for monitoring your system

Local Model Context Protocol (MCP) server for Google Tasks

A Model Context Protocol server for reading local files

MCP Server using local embeddings to search user-provided ETABS documentation.

Give OpenAI agents the ability to securely spawn and govern local models like Qwen and DeepSeek

Building the Custom MCP server that list, read, and write directly in our Local environment using the Gemini's flash-lite-preview