"MCP servers that use streamable HTTP as transport" matching MCP servers:

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Enables Claude Code, Cursor, and other AI tools to call OpenAI Codex for task execution, with safe and writable modes.

Enables AI coding agents to read and write a user's Figma file through the Figma Plugin API, offline and privately, without API tokens or rate limits.

Delegates coding tasks to the local Claude Code CLI via MCP, offering run, review, and status tools for MCP-compatible agents.

An MCP server that exposes your local Claude Code CLI over HTTP+SSE, enabling any MCP-compatible client to use your Claude Code MAX/PRO subscription remotely.

Enables structured, step-by-step problem-solving through dynamic thinking processes that can be revised, branched, and adjusted as understanding deepens. Supports breaking down complex problems into manageable steps with the ability to revise previous thoughts and explore alternative reasoning paths.

Provides brutally honest code reviews, explanations, and refactoring suggestions via CLI and MCP tools.

An MCP server that allows coding agents to search the Swift Package Index and retrieve GitHub READMEs without requiring an API key. It features comprehensive search filters for stars, platforms, and licenses, providing token-efficient responses optimized for LLM comprehension.

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

Enables Claude Code to use GLM (Zhipu) as a cheap, full-capability subagent for file editing, code generation, and bash commands, with automatic routing between Opus and GLM based on task complexity.

Simple sequential thinking MCP in python

Enables AI assistants to control running Neovim sessions via RPC socket, supporting command execution, state inspection, and LSP actions. Automatically discovers Neovim instances and supports multi-instance management on Linux and macOS.

An MCP server for running Claude Code and the Codex CLI as a pair: Claude drives, and hands self-contained tasks to Codex as background jobs.

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.

A Model Context Protocol (MCP) server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. Developed by Mammoth Growth.

MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.

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.

A minimal local MCP server that lets Claude Desktop or Claude Code delegate coding tasks to Grok Build running headless as a subagent.

MCP server that turns Kimi K2.6 Turbo into an agentic coding assistant with tools for file operations, shell commands, and code search.