"Socket" matching MCP servers:

A Model Context Protocol (MCP) server for Socket integration, allowing AI assistants to efficiently check dependency vulnerability scores and security information.

Enables AI assistants to search and browse an independent directory of 800+ open-source MCP servers by keyword, category, or use case, and to fetch individual server details, README-derived features and requirements, and known install configs. All tools are read-only, require no authentication, and are served over streamable HTTP.

It enables MCP integrations to safely access a chosen project folder with path-boundary enforcement, read and search files, and perform confirmed writes over a bounded local Unix-socket transport.

An independent messaging-channel bridge for Claude Code, with Slack Socket Mode adapter; enables Claude to receive and respond to messages via Slack.

A server that bridges MCP tool calls to JSON-RPC function calls over socket connections, allowing external applications to expose functions as MCP tools.

A Node.js MCP server that acts as a communication bridge for the HandsAI Java application, enabling socket-based integration between MCP clients and the HandsAI main server.

Enables AI assistants to control running Neovim sessions via RPC socket, supporting command execution, state inspection, and LSP actions. Automatically discovers Neovim instances and supports multi-instance management on Linux and macOS.

One todo list every AI coding agent can write to — Claude Code, Codex, Cursor — scoped per project, local-first, self-hostable.

Enables AI assistants to directly control Autodesk 3ds Max through natural language to create models, set materials, adjust lighting, and automate animations. It bridges the Model Context Protocol with 3ds Max via a TCP socket to execute Python and MAXScript commands.

Lets you @mention a bot in a Slack channel or DM to send work to a local Claude Code session and watch it run, with live self-updating turn cards, threaded answers, progress checklists and a per-channel inbox with read cursors. It runs entirely on your machine over Slack Socket Mode—no tunnel or public IP—routes misdelivered messages to the right project, and masks credentials in anything it posts back.

MCP server that exposes the Herdr terminal API as callable tools, enabling AI agents to manage terminal workspaces, tabs, panes, and agents. It dynamically generates tools from the Herdr API schema and communicates via Unix socket.

Lets AI agents drive terminal apps built with Limoni (a Go TUI engine) through their semantic tree instead of scraping the screen: widgets are found by role and label, clicked, typed into, and waited on. Runs locally over the app's automation socket; secret fields never reach the agent.

A small, readable MCP learning project implemented in TypeScript that uses a local JSON notebook to demonstrate core MCP features such as tools, resources, prompts, sampling, and notifications.

Reads the Claude Code, Codex and OpenCode usage logs already on your machine and reports token totals, per-day and per-hour activity, a per-agent and per-model breakdown, and a year-in-review recap. It makes no network request at all — a test fails if any source file in the package can open a socket.

Drive the Unreal Engine 5.7 editor from any MCP client over a local TCP socket - 105 editor-automation tools (72 native C++ handlers + 33 bridge-side): actors, levels, materials, Blueprints, sequencer, rendering, asset import, editor Python. Native C++ plugin + thin Python bridge, ~50ms round-trips. MIT.

Enables direct interaction and control of SketchUp through Claude AI using the Model Context Protocol and a TCP socket connection. It allows for prompt-assisted 3D modeling, component manipulation, and the execution of arbitrary Ruby code within the SketchUp environment.

Enables control of a Rigol MHO98 oscilloscope over VISA (raw TCP socket or USBTMC) through 142 SCPI-backed tools covering acquisition, triggering, measurements, waveform and bus decoding, built-in AWG, display, analysis, and instrument-side storage. Waveform and screenshot data are written to disk with statistical summaries returned, keeping large sample arrays out of the model context.

Provides a unified MCP server for the SimLiverse Physical AI Platform, enabling LLM copilots to access Isaac Sim knowledge via NVIDIA NIM and execute/control simulation through a TCP socket.

Enables read-only inspection and narrowly scoped maintenance of a local Docker Desktop environment, covering containers, images, logs, stats, Compose status, and Scout vulnerability/SBOM data, plus limited actions such as image pulls, container restarts, dangling-image pruning, and allowlisted Compose redeploys, all without exposing the raw Docker socket to the client.

Lets a Codex session launch, bind to, and drive its own dedicated Claude Code session running in a cmux terminal surface, over the cmux socket via an MCP bridge. Provides session discovery, keyed and idempotent message delivery with transcript-verified acceptance, waiting/observation, compaction, and lease- and permission-guarded control of the bound session.