"Box" matching MCP servers:

A local-first external context box for coding agents, providing indexed file metadata, document/image extraction, and durable chat preservation via MCP tools.

Enables clients to add, retrieve, update, delete, and list notes persisted to a local JSON file, with path configurable via an environment variable or command-line flag. Writes are atomic and locked, and a missing note raises an error rather than returning a placeholder string.

Enables s&box teams to coordinate coding agents and editors through shared tasks, file reservations, handoffs, builds, and change notifications, using GitHub as the source of truth.

Provides tools for interacting with SQL Server databases, enabling users to retrieve paginated table data, inspect schemas, and count records. It features enforced pagination and secure configuration options to manage database operations efficiently through natural language.

An MCP server for interacting with SQL Server databases that enables schema inspection, record counting, and paginated data retrieval. It provides tools to explore table structures and fetch specific records while enforcing safety limits on data volume.

An MCP server that converts HTML to PDF with built-in fonts, CSS, and streaming, enabling AI agents to generate static PDFs from HTML strings.

An MCP server for downloading academic papers from multiple sources using intelligent routing and year-aware priority selection. It enables users to retrieve metadata and download single or batch PDFs by DOI or URL.

An MCP server that enables AI assistants to discover and execute Nox sessions for project automation tasks like testing, linting, and building. It provides tools to list available sessions and run them using specific Python versions, tags, or keyword expressions.

This server enables AI-assisted APK reverse-engineering entirely on-device, orchestrating jadx, apktool, adb, frida, and APKiD through a job/workflow engine, and exposing those agents as native MCP tools for Claude without any cloud dependency.

A Model Context Protocol (MCP) server for Firebird databases intended for local use. It reads connection details from FlameRobin's fr_databases.conf so no extra configuration is needed — if you have FlameRobin set up with your Firebird databases, this server works out of the box.

Enables Codex to trigger an animated hand on your desktop that delivers playful cartoon slaps when mistakes are detected, with severity-based slap counts, while the agent continues working.

A local-first MCP server for shared memory across AI tools, enabling context capture and resume across sessions.

AgentBridge is a local MCP server that lets Claude Code delegate coding tasks to external CLI workers like Codex and Antigravity. It assembles structured prompts, runs the workers with git snapshotting, and returns compact structured results without running its own models.

Enables AI assistants to save resolved debugging sessions as concise experience cards into a local JSON knowledge network, and to retrieve relevant past cards when new bugs arise. It also powers a spaced-repetition review interface to reinforce memory of those experiences.

MCP server for generating properly aligned ASCII, Unicode box-drawing, and Markdown tables, with correct width measurement for Thai, Pali, and CJK characters using wcwidth.

MCP server for VibeKit — build, deploy, and manage hosted apps and chat with each app's persistent server-side AI agent from Claude Desktop, Cursor, or any MCP client. Every app gets its own agent and a live URL; bring your own Claude/OpenAI key or pay-as-you-go.

Enables MCP clients like Claude Code and Cursor to use multiple AI models (Gemini, GPT, Grok, DeepSeek, Kimi, Ollama) via a unified chat tool with conversation memory.

Provides tools for Cursor to interact with IBM Bob Shell, enabling Bob-powered coding assistance, session management, and task delegation directly from Cursor.

Provides AI assistants with intelligent access to project documentation and API references through smart search, contextual rules, and Docset integration. Enables AI to understand project-specific conventions, patterns, and official framework documentation without token limits.

Enables an AI agent to take full control of a machine — running shell commands, editing files, managing git, packages and processes, and reaching the network — with batched execution, server-side variables and selectable tool profiles that keep token usage low. It also speaks HTTP so the same agent can operate a remote build box, NAS or VPS.