"Socket" matching MCP servers:

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.

Deterministic AST deconstruction and runtime circuit breaker preventing rogue shell escapes, dynamic eval(), and covert lateral socket egress in autonomous LLM tool calls.

Linux desktop HAL for AI agents. One daemon, one socket, every desktop action. GNOME, KDE, Hyprland, X11. Ships in one command.

Lets MCP clients such as Claude Code, Cursor, and Claude.ai inspect and drive herdr workspaces, panes, and coding agents over a local socket, running either as a local stdio process or as an OAuth-protected HTTP endpoint published through a Cloudflare Tunnel. It exposes tools to create workspaces and tabs, split panes, start and prompt agents, read their output, and wait for results.

Enables context-loop navigation in agents by exposing goto and loop_start_marker tools that delegate to a host over a Unix socket, allowing bookmarking and jumping between context iterations.

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.

Local-first persistent memory layer for AI agents. Provides hybrid search (FTS5 keyword + vector embeddings) over 223K+ knowledge chunks via MCP. Tools: brain_search, brain_store, brain_entity, brain_subscribe. Features pub/sub with stable agent identity, delivery tracking, and Claude --channels integration. SQLite + BrainBar Swift daemon on Unix socket.

Enables AI agents to spawn, coordinate, and message worker cells via a single MCP server over a local Unix socket.

MCP server for LeekWars game enabling AI management, fight operations, item handling, and real-time socket communication via authenticated session.

Enables AI assistants to interact with the PocketOption trading platform via MCP, including balance checks, candle data, asset screening, and trade placement, with support for multi-agent coordination.

Enables AI agents to search, describe, and call paid data services from the Pocket Network agentic marketplace, paying per request in USDC via x402.

Automatically converts JavaScript modules into MCP-compatible servers, making any JavaScript function accessible to AI systems through secure sandboxing with automatic type inference.