"Rocket" matching MCP servers:

Enables teams to ask questions and perform operations against Rocket UniVerse and UniData systems from MCP clients, with per-connection role-based access, SSO, and admin-managed permissions. Provides tools for records, queries, dictionaries, BASIC subroutines, transactions, exports, and saved knowledge across multiple U2 connections.

Generates customized, production-grade MCP servers for Rocket.Chat by selecting only the specific API endpoints needed for a project to minimize context bloat and token usage. It uses natural language processing to parse official OpenAPI specs and automatically create optimized TypeScript servers with built-in authentication and tests.

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

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

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.

A FastMCP (Python) server for Rocket.Chat with 28 tools covering channels, messages, threads, DMs, files, users, and analytics, plus AI governance, observability, and security features.

RocketRide is a self-hosted, open-source AI pipeline platform (MIT) that exposes pipelines as MCP tools. Supports Claude, OpenAI, Gemini, and xAI. Pipelines connect via WebSocket and are made available to MCP clients like Claude Desktop, Cursor, and Windsurf.

Enables coding agents to query a local OTLP trace collector: list recent traces, inspect span trees and critical paths, flag SQL N+1 loops, surface gen_ai metrics, and diagnose slow traces with a local OpenAI-compatible model.

A thin stdio-to-HTTPS proxy that connects local MCP clients to the hosted Voris MCP server, forwarding JSON-RPC messages verbatim.

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

Enables testing whether a ChatGPT account can render and interact with custom MCP widgets, using a mock spending card with buttons that trigger tool calls and update state.