"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Bridges MCP clients to the DeepSeek API for chat completions and model discovery, with an optional locked-down bridge that delegates prompts to local CLI harnesses like Claude, Codex, or opencode.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

A tool for detecting and cleaning Java memory shells via local or SSH remote execution. It enables AI agents to scan Java processes, analyze suspicious class code, and safely remove memory shells after user confirmation.

Safety-gated SSH MCP server for DeepSeek Harness and standard MCP clients, enabling agents to use a laboratory server's GPU, runtime, and configured source workspace while keeping the server isolated from the public internet.

A server that manages conversation context for LLM interactions, storing recent prompts and providing relevant context for each user via REST API endpoints.

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

Enables any MCP client to execute DeepSeek Harness agents and shell commands through standard MCP tools, bridging multi-agent capabilities with sandboxed execution.

Provides the current date in multiple formats (e.g., European, ISO, US) via a simple MCP tool.

Hardware probe MCP server that provides deep hardware inventory and live sensor telemetry for AI agents, including CPU, memory, disk, GPU, and sensor data across platforms.

Enables AI assistants to monitor and manage Linux infrastructure including services, logs, processes, disk, memory, ports, cron, nginx, Docker, and system health checks via the Model Context Protocol.

A minimal MCP server that exposes a single tool to query local hardware information (OS, CPU, memory, architecture).

Runs AI-generated code in secure Firecracker microVMs with opt-in network policy enforcement, PII scanning, prompt injection defense, and audit logging. Exposes MCP tools for running commands, managing files, and the full sandbox lifecycle.

Enables AI assistants to flash firmware, program memory, modify option bytes, erase chips, reset boards, and capture SWO printf traces for STM32 microcontrollers via STM32CubeCLT.

Sandboxed bash execution MCP server for AI agents, using an in-memory virtual filesystem overlay to prevent real filesystem damage, with configurable network access, timeouts, and optional Python/JS runtimes.

Provides Ubuntu system information (CPU, memory, disk, network, services, processes) to Bob via natural language queries.

A Model Context Protocol server that generates lightweight ASCII charts directly in terminal environments, supporting line charts, bar charts, scatter plots, histograms, and sparklines without GUI dependencies.

Enables AI assistants to start and manage LLDB debugging sessions, including loading programs, setting breakpoints, stepping through code, and examining memory.

Turns an Agent client into a local-first workbench with tools for files, grep, patching, commands, web search fallback, memory recall, and model-backed agent tasks.

A Node.js implementation of the Model Context Protocol that provides secure shell command execution capabilities, allowing AI models like Claude to run shell commands in a controlled environment with built-in security measures.

Turn any REST API into an MCP server in one command. Point mcpify at an OpenAPI spec and every endpoint becomes a tool your AI agent (Claude, Cursor, Windsurf) can call — zero glue code, always in sync with the spec.