"Persistent" matching MCP servers:

Enables AI assistants to execute Julia code efficiently with persistent sessions, avoiding startup costs and maintaining state across calls.

Provides Prolog logic programming integration for Claude via a Docker SWISH container, with persistent notebooks and cognitive architecture support.

Async Python REPL + Shell execution for MCP. Provides persistent state, background jobs, interactive input() bridging, and crash isolation in a single server.

A production-ready MCP server that equips AI agents with dynamic, persistent, and executable skills. It enables secure script execution and progressive disclosure to reduce context window usage.

MCP server giving agents a persistent IPython workbench and a brokered RLM engine for durable, stateful computation. Offers 30 tools for bounded model calls, artifacts, and receipts with host-owned authority.

A localhost broker that allows multiple MCP clients to share a persistent xcrun mcpbridge connection to Xcode, enabling tool discovery and serialized calls.

Enables AI agents to safely run bounded, sandboxed tasks on remote machines with persistent state and reviewable artifacts.

Provides a stateful Django shell environment that allows AI assistants to execute Python code directly against Django projects. Maintains persistent session state between calls, enabling iterative exploration of models, queries, and debugging.

Provides a persistent Python REPL session as a tool for executing code, managing files, installing packages, and initializing projects via the MCP protocol.

Bridges Xcode's mcpbridge to MCP clients via SSE, maintaining a single persistent process to eliminate repeated authorization prompts.

A self-hosted MCP server providing Claude with an interactive Jupyter environment, including real kernels, persistent notebooks, and optional GPU offload to Google Colab.

An MCP server that connects to existing IPython kernels, allowing Claude to execute code in a shared persistent environment with your IDE.

Enables persistent remote VPS collaboration with MCP tools, live dashboard, and autonomous AI agent for code execution, memory, and task automation.

Enables AI coding assistants to query a persistent local code graph for targeted context, blast-radius analysis, and incremental updates, so they read only relevant files during reviews and large-repo workflows.

CCR gives MCP-capable AI agents persistent project memory, strategy playbooks, and a sandboxed Python REPL.

Enables MCP clients like Claude Code to delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions that resume across calls.

Enables creation and management of persistent REPL sessions for various languages and shells, with web-based monitoring and session recovery capabilities.

Persistent memory and pattern learning for AI coding assistants via MCP.

An MCP server that enables AI assistants to interact with q/kdb+ databases for development and debugging workflows. It supports executing queries, persistent connection management, and includes a Qython translator for converting Python-like syntax to q.

Enables AI assistants to execute Ruby console commands (Rails console, IRB, etc.) with persistent session support for interacting with Ruby/Rails applications through natural language.