"Zsh" matching MCP servers:

Launches the official Codex CLI as a persistent MCP server so DeepSeek Harness can invoke Codex models without storing or transmitting ChatGPT credentials to third parties.

Enables external MCP clients to drive DeepSeek Harness agents for real coding tasks, providing tools for task execution and queueing, session management, sandboxed file access, preset switching, and usage statistics.

Exposes DeepSeek Harness's coding agent as a model backend via MCP, with user-confirmed task execution and self-inspection/config-patch tools.

Enables unified access to a multi-node DSH control plane, routing ChatGPT tool calls to appropriate node agents with presence awareness, health monitoring, and fail-closed execution.

Exposes DeepSeek Harness agent capabilities as an MCP server, letting any MCP client drive Harness to execute real coding tasks with structured results, context isolation, and parallel execution.

Enables claude.ai, including free users, to act as a coding agent on your own machine, allowing file edits, shell commands, and git operations within explicitly chosen project folders. It provides a secure local MCP server exposed as a custom connector with OAuth-based consent.

This MCP server enables automated maintenance and code analysis for Python/pytest repositories in isolated Docker environments. It supports read-only investigations, fix-and-verify tasks, and provides full audit trails with SQLite event history and artifact exports.

Transforms Claude into a production-grade pair programmer by orchestrating best-in-class APIs (Morph, Chroma, DSPy) for iterative code evolution to 95%+ quality, semantic codebase search, package discovery across 3,000+ libraries, and pattern learning.