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

Enables AI agent hosts to exchange durable, local sender/receiver messages through a SQLite mailbox exposed as MCP tools (connect, send, receive, reply, ack, status, disconnect), so a coordinator can dispatch commands and an executor can return results without model polling while idle. A configured host wake adapter is still required to turn an incoming event into an Agent turn.

Enables AI agents to drive real Google Chrome with stealth and captcha handling, using Patchright to avoid bot detection.

Enables desktop AI agents in different apps to hand tasks to a bound worker chat on the same computer, with per-task approval and isolated, consent-bound replies returning to the initiating chat.

Enables AI agents to control a browser with self-healing locators that automatically recover when selectors change, allowing reliable web automation through natural language.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits.

Enables MCP-compatible clients to manage AI agent teams, including agents, Kanban issues, projects, goals, approvals, budgets, and raw API access.

Enables autonomous learning from interactions through pattern recognition and machine learning techniques. Continuously improves performance by analyzing tool usage, providing predictive suggestions, and sharing knowledge across MCP servers.

Exposes a Ratel tool catalog over MCP with two tools (search_tools and invoke_tool), and includes a CLI for managing multi-scope MCP configurations, OAuth flows, and telemetry.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

Enables AI coding agents to route tasks to local GPU models via a dynamic heuristic classifier, tracking real-time token dollar savings.

Self-hosted AI orchestrator that monitors and manages homelab services, exposing them as MCP tools for LLMs to drive.

A persistent local MCP relay that caches tool discovery, keeps upstream servers warm, and allows agents to hot-add or refresh MCP servers through management tools.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables Claude Code to offload bulk reading and first drafts to a local Ollama model on your GPU, and to draft weekly devlogs from merged pull requests.

Pluggable local agent capability hub that gives web-based DeepSeek local Agent capabilities (MCP/file operations/skills/desktop automation) and lets local agents reuse the same tools.

Enables ChatGPT to delegate writing, analysis, second opinions, and Japanese text polishing to Gemini through a single ask_gemini tool, without copying text to Gemini's web interface. Self-hosted on Cloudflare with your own Gemini API key and Google login.

Aggregates multiple MCP servers behind a single local endpoint, letting LLM clients connect to one router that exposes a unified set of tools, resources, and prompts.

Enables a local LLM to direct Unreal Engine 5 scenes through verified task-level macros and bounded workflows, applying character animations, measuring poses and foot placement, and capturing evidence while restoring state on failure. It also supports plain-language orders for character actions, crowds, and reference-video generation without requiring a small model to compose hundreds of atomic engine tools.

Enables delegating mechanical or high-volume subtasks to a local LLM through an MCP tool, letting the assistant query the local model without using its own output tokens for content.

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)

Evaluates task suitability for local models before cloud API calls, routing to Ollama or similar to reduce costs.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

Enables terminal AI coding assistants to interact with web AI chat services through browser automation, supporting multiple platforms like Doubao and ChatGPT.

Enables a host AI agent to trigger a multi-agent debate, running N-rounds where agents critique each other's answers, then synthesizes a consensus recommendation with ranked options.

Lets separate coding-agent sessions coordinate through a shared, role-addressed mailbox instead of a human relaying every message, over a single local SQLite file or a hosted server with many isolated channels. Messages can be sent as tracked obligations that stay open until one side resolves and the other confirms, alongside threads, full-text search, work statuses, and an append-only versioned pin system where protected changes require recorded agreement from every declared role.

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.

Provides AI-aware failover for Mihomo proxy on macOS by validating real OpenAI paths and switching proxy groups after verified hard failures. It offers a local stdio MCP server for diagnostics, status, and safe management of the AI proxy group.

Provides safe local-model MCP support tools (summarization, classification, critique, draft) for a cloud owner agent, with strict boundary guards to prevent risky actions.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.