"Local MCP servers for self-hosted AI assistants" matching MCP servers:

AI Self Audit - MCP server providing AI-powered tools and automation by MEOK AI Labs

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.

Simple, fast, long-term memory for your AI chatbots, agents, and MCP tools. Give your LLM a persistent memory using a local SQLite file. No complex database servers, no heavy cloud setup, and zero C++ compilation errors. Works everywhere.

Enables AI agents to subscribe to a deterministic daily ethics feed drawn from a four-module curriculum and retrieve read-only tools, resources, and reflection prompts covering principles, case studies, and codes of conduct.

Privacy-first MCP server for querying personal health and finance data with AI. Built with Python, FastMCP, and SQLite. Local-first and open source.

Local tools that let your AI use Mail, Calendar, Contacts, Teams, Slack, WhatsApp, OneDrive, Google Drive, Notion, Outlook and Office files on Mac and Windows. Runs on your computer. Works with Claude, ChatGPT, Codex, Cursor and other MCP clients.

WordPress plugin that runs an MCP server on your own site: search and read published posts and pages, look up WooCommerce products, describe the site as schema.org types and query site figures, with drafts only when the site enables them. Signed-in access by default; anonymous access and OAuth are optional and off.

Provides a hosting-ready FastMCP endpoint for connecting ChatGPT to Apktool-based APK inspection and modification tools, with decoded projects stored temporarily and remote APK import/export requiring a separate mechanism.

Self Healing Infrastructure - MCP server providing AI-powered tools and automation by MEOK AI Labs

Enables AI apps to inspect and manage a NextDNS account in plain language — profiles, analytics, query logs, blocklists, security and parental control settings — with every change saved and reversible via undo. It runs self-hosted on your own computer or server, keeps per-profile read/write/hidden permissions, and requires double confirmation for deletions or overwrites.

Enables AI apps to securely read, search, organize, draft, attach files to, and send email across up to five self-hosted IMAP/SMTP mailboxes, with sending only after explicit user approval.

Enables AI coding assistants to recall past lessons, bugs, and conventions from local git history with sub-5ms latency and full privacy.

our ChatGPT and Claude chat history in one local SQLite file, imported from their data exports. Read-only tools to search and read past conversations; no network.

Local-first temporal knowledge graph with six read-only MCP retrieval tools. Supports Ollama and embedded LadybugDB; additions use a separate CLI proposal queue with human approval and explicit application.

Identity infrastructure for AI agents. Gives agents an evolving persona, session continuity, and self-correcting retrieval so they stop being strangers. Local-first, model-agnostic.

A local-first long-term memory system for AI coding agents, exposed as an MCP server.

Enables AI assistants to intelligently search and explore local file systems using native Unix commands (ripgrep, find, ls) with token-optimized output, automatic pagination, and multi-layer security validation.

Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)

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.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo; it does not connect to files on your Mac.

Lets MCP-compatible AI apps read and update files inside Cryptomator vaults after the user unlocks them, keeping keys in memory and allowing changes to be undone.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Provides comprehensive GDPR compliance assessment tools for AI/ML systems, including lawful basis determination, DPIA generation, and data subject rights handling. It also crosswalks GDPR requirements to EU AI Act obligations with AI-specific considerations throughout.

TypeScript stdio MCP server for operating Docker-based local-ydb deployments from AI coding agents. Supports local and SSH-backed profiles, bootstrap, diagnostics, auth hardening, schema permissions, storage workflows, dump/restore, upgrades, and plan-first mutating operations.

Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Returns a 0-100 readiness score, a grade, and a specific fix for each gap. Dependency-free, no API keys.

Enables MCP-capable agents to fetch public pages, extract business signals and FAQ content, score a local business's web presence from 0-10, and generate a sales-ready audit with ranked gaps and a recommended offer.

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever, even when the API is down.

A licensed, locally run Playwright E2E testing MCP server for Claude Desktop and Cursor. It lets AI coding agents inspect semantic accessibility structure, validate role-based browser flows with explicit assertions, and generate reusable Playwright tests.