"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.

Enables AI assistants to access Swiss public transport data including journey planning, real-time departures, disruptions, occupancy forecasts, ticket prices, and train formations via a standardized MCP interface.

Provides a generic HTTP client tool allowing AI agents to make arbitrary HTTP requests from their environment, with support for environment-variable placeholders for secrets.

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

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Provides Estonian public transport timetables, trip planning, stop search, and real-time vehicle tracking.

Deterministic SNAP eligibility logic, exposed as auditable Model Context Protocol tools. An AI agent can read, reason, and orchestrate, but the eligibility determination itself is made by versioned, tested, cited code that a caseworker, an auditor, or a court can inspect.

MCP server for Swiss public transport — connections, stationboards, real-time delays, and direct booking links for SBB.

Multi-account X (Twitter) automation that drives a real Chrome session with your own cookies, so no X API key is needed. 32 tools for posting, replies, search, engagement, and media, with draft approval on by default.

Enables agents to interact with CLI applications like vim, htop, and gdb by sending key inputs and capturing terminal output through tmux sessions.

Enables interaction with Jenkins servers through HTTP APIs, allowing users to list jobs, trigger builds, view logs, and manage configurations without requiring plugins or admin access.

Enables Claude to see and control a real Android phone via MCP, reading the accessibility tree to tap, type, navigate, launch apps, and diagnose connectivity over ADB or cellular.

A workspace of six MCP servers—grounded-cv (hybrid RAG with citations), repo-intel (GitHub repo intelligence), web-research (safe web search/extraction), ats-jobs (unified ATS job boards), outcome-ledger (durable task ledger), and coding-workflows (code review & planning)—purpose-built for agentic hiring evaluations.

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.

Enables AI agents to drive a Linux/X11 desktop via AT-SPI accessibility-tree perception and element-level actions, avoiding screenshots and coordinate clicking.

Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.

Enables an agent to see and operate a GNOME Wayland desktop like a human, including screenshots, mouse/keyboard control, accessibility tree access, OCR, clipboard, and audio listening.

A low-level computer-use MCP server that exposes raw desktop control (mouse, keyboard, shell, windows, processes, screenshots, etc.) to MCP clients like Claude Code and Codex.

Local + remote terminal interaction control MCP Server. Lets AI agents control interactive TUI programs the way a human would.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.