"Using llama.cpp and Searxng with local models" matching MCP servers:

A generic OpenAI-compatible subagent MCP server that lets Claude Code delegate coding grunt-work to a local model via a tool-calling agent loop, with configurable concurrency and backend.

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 Codex to delegate coding tasks to a locally hosted Qwen model through an MCP tool, which can read, write, patch, test, and inspect git diffs inside an allowed workspace.

Bridges Claude with a local Ollama coding model, letting Claude delegate bounded implementation tasks to the local model while retaining reasoning, review, and safety enforcement.

Enables ChatGPT to work directly on local projects by reading files, editing code, running tests and commands, inspecting Git state, and managing durable workflows, with optional delegation to local Codex agents for complex tasks.

A Windows proof-of-concept MCP server that connects ChatGPT developer-mode to a local Codex CLI via Secure MCP Tunnel, exposing a small set of read-only, allowlisted tools in an isolated workspace.

MCP server that enables delegation of small coding implementations to a cheaper language model with propose_patch and apply_patch tools, while the primary agent retains architecture, review, and approval.

Enables ChatGPT or other MCP clients to control native Codex sessions on Windows, providing tools for thread management, turns, observation, steering, and responding to approvals.

An MCP server for local Cocos Creator 3.8 automation, enabling coding agents to create projects, edit scenes, and build WeChat Mini Games directly on a developer machine.

Enables MCP clients to run Cline CLI prompts and isolated repository-wide analyses, returning terminal text responses with model, duration, and usage/cost.

Enables AI coding agents to drive the E-language IDE locally through MCP tools, allowing them to read, search, edit, and compile .e/.ec source files with workspace mirroring and instance routing.

Enables a local-first autonomous coding agent that plans, edits, and verifies code using LM Studio, Ollama, or llama.cpp models, with hardware-aware parallel sub-agents and optional frontier-model planning.

Enables a portable Windows coding agent to perform file editing, process management, package operations, testing, and Git workflows within configured project boundaries. Also provides managed background process sessions and Git linked worktree management.

dev-brain-mcp

MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.

MCP server for Python build123d to help AIs develop and reason about 3D models and CAD

Wraps the local Qoder CLI into an MCP server, enabling any MCP client to delegate coding tasks to a local Qoder agent with session management, sandboxed permissions, and model selection.

MCP server that enables cloud models (like Gemini/Claude) to delegate coding tasks to a local llama.cpp server, preserving cloud usage limits through an AI-powered code review loop.

This MCP server enables LLM hosts to plan large tasks and delegate subtasks to specialized local CLI agents, such as Codex and Claude Code, using tools like delegate_task and get_agent_roster.

Enables MCP clients to invoke Cursor SDK's agent runtime, run coding agents, list models, and continue conversations.