"Utilizing Local LLMs for Query Preprocessing with Minions Framework" matching MCP servers:

Enables ChatGPT web to read local files, search code, run shell commands, and drive a local Codex CLI via an official MCP connector, with human approval for risky commands and full audit logging.

Generates project features (HTML pages, backend APIs) from prompts and project-specific business rules stored as resources, with support for interchangeable LLM providers (local Ollama or cloud Gemini).

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 any LLM to drive your local Codex CLI in a sandboxed workspace, running coding tasks and generating images without needing an API key.

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.

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.

Enables ChatGPT to inspect selected local projects, make edits, run commands/tests, and review diffs through an authenticated MCP endpoint backed by a containerized workspace.

A local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.

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.

A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews.

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 MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.

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.

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.

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

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.

Bridges Claude Code CLI with Cursor IDE to use your existing Claude subscription without separate API costs.

Connects the ChatGPT web app to a locally running Codex agent over OAuth-secured MCP so users can plan in chat while their own machine reads authorized project files, applies SHA-guarded edits, and runs sandboxed tests. Per-project grants can be revoked anytime, and every write is backed up, conflict-checked, and audited.

Enables a cloud coding agent to delegate a focused coding task to a local Ollama or OpenAI-compatible model through a bounded workspace, file allowlist, and required external checks. Changes are applied only after verification against the declared scope, with failed post-apply checks rolled back and the rollback itself confirmed.