"Local" matching MCP servers:

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

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.

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.

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 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.

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 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.

Enables coding agents like Claude Code and Codex to offload boilerplate generation, summarization, and other bounded text tasks to local or cheap cloud LLMs, keeping the frontier agent in charge of judgment and code edits.

Lets local MCP clients use one LightNow-managed MCP entry instead of storing every MCP server configuration and secret in every client.

Enables external AI supervisors to oversee and steer native Codex through MCP, including thread and turn management, observation, interruption, approval responses, runtime status, and checkpointing.

Enables AI clients to access many MCP servers through localhost HTTP endpoints, running each server once in a single Node process to avoid duplicated stdio spawns.

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 local control of existing Chrome/Chromium browser tabs through MCP, including tab management, navigation, content reading, screenshots, and page interaction.

An MCP control plane for Codex native sessions, translating eight explicit operations with strict security boundaries for authenticated access through OpenAI Secure MCP Tunnel.

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.

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

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

Enables ChatGPT to securely control a local workstation via an MCP tunnel, exposing 44 tools for file/project editing, git, process supervision, browser automation, and Office document handling across macOS, Linux, and Windows.

Run the open-source n8n-mcp locally and connect your n8n instance to MCP-compatible AI agents like Codex and Claude Code.