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

Persistent memory MCP server for AI agents, using SQLite with hybrid keyword and semantic search for long-term memory storage.

Provides CodeQL language intelligence to AI agents via MCP, enabling completions, hover, definitions, references, diagnostics, formatting, and in-memory file updates for QL code.

Enables exploring Microsoft Fabric / Power BI workspaces and semantic models, and executing ad-hoc DAX queries.

Enables querying and exploring Cribl Stream and Edge deployments, providing access to worker groups, fleets, sources, destinations, pipelines, routes, event breakers, and lookups through a structured interface.

Provides tools to search and retrieve news across various categories including business, technology, science, and sports via the Google News API. It supports keyword searches, autocomplete suggestions, and region-specific news across multiple languages.

A personal memory engine and MCP server that stores durable facts in markdown files managed via git, enabling hybrid search (lexical + semantic) through an MCP interface for persistent context across LLM sessions.

Sandboxed Python execution with automatic dependency management. Executes Python scripts in isolated environments (bubblewrap or Docker) with PEP 723 inline dependencies, preventing host pollution.

Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.

Enables Claude to speak in 70+ languages, including pronunciation, audio flashcards, and full language lessons with tutor personas.

MCP server for the Trading 212 public API, enabling account, portfolio, order, pie, and history access with read tools always available and trading tools opt-in.

A multi-agent RAG MCP server that answers questions from your documents with a human-in-the-loop approval step, using a coordinator, retriever, and synthesizer agents.

Bridges a local AI agent to a Colab session in the browser, enabling code execution and file operations through the Model Context Protocol.

An MCP server that fetches web pages and extracts clean, AI-friendly Markdown content using Mozilla Readability. It provides secure web access for LLMs with built-in SSRF protection and automated content cleaning for improved context retrieval and summarization.

A demo MCP server exposing billing operations (invoices, customers) with no built-in safety, designed as a test target for NitroWatch governance. It allows reading, sending, archiving, and permanently deleting accounts/invoices without confirmation.

Ultra-fast web fetcher and MCP server written in Rust. Fetches any URL as clean Markdown with HTTP/3, JavaScript rendering, anti-fingerprinting, browser cookie authentication from Chrome/Firefox/Brave, and 1Password integration.

Enables LLM-driven agents to autonomously detect, diagnose, repair, verify, and prevent software and hardware failures on local and remote systems. Includes built-in safety checks and automatic rollbacks.

An MCP server for bridging your local agent to a Colab session in the browser.

Run AI agents in Zulip as @mentionable bots — or wire into any MCP client.

Enables human-in-the-loop interaction for AI coding workflows through native desktop dialogs that present route choices, text input, and image annotation capabilities when AI assistants encounter decision points.

A Model Context Protocol server that provides programmatic APIs for running mutation tests with mutmut, analyzing results, and improving test coverage in Python projects.