Production-ready MCP Server Framework with built-in logging, metrics, sessions, and multi-transport support.
Lightweight HTTP MCP Server framework
Generic MCP server framework with tool registration, validation, and error handling
Production-ready MCP server framework with concurrency control, auth, and observability
MCP server framework — defineServer, defineTool, 19 plugins, storage, transport
Lightweight MCP server framework. Tool visibility control through middleware.
MCP server framework for building Model Context Protocol servers
Production-ready MCP server framework with HTTP + webhook-based subscriptions
Augments MCP Server - Framework Documentation Provider for AI Assistants
NitroStack - Enterprise-grade MCP server framework. Decoupled into @nitrostack/core, @nitrostack/cli, and @nitrostack/widgets.
Bun-native MCP server framework
MCP server framework with per-tool-call BTX service-challenge admission. Gate any agent tool behind chain-anchored proof-of-work. Companion to @btx-tools/challenges-sdk.
Library-form fork of freee/freee-mcp. Exposes the MCP server framework, API client, OpenAPI schema loader, and skill resources as npm library exports for use as a dependency, while preserving upstream CLI binary compatibility.
MCP server framework with Express, middleware pipeline, and tool orchestration
MCP server framework with typed tools for Outfitter
A community-driven MCP server framework that lets anyone expose personal information to AI assistants via the Model Context Protocol.
Tools for writing MCP clients and servers without pain
Framework for building Model Context Protocol (MCP) servers in Typescript
[](https://serverless.com)
A TypeScript SSE proxy for MCP servers that use stdio transport.
Dversi MCP Server Framework - Universal tools and HTTP transport
The official TypeScript library for the Cloudflare API
Model Context Protocol implementation for TypeScript
A TypeScript framework for building MCP servers.
Adaptive prompting techniques, K-means task clustering, and temperature optimization for the Brainwires Agent Framework
Speech (TTS / STT) provider clients for the Brainwires Agent Framework — Azure Speech, Cartesia, Deepgram, ElevenLabs, Fish Audio, Google TTS, Murf, plus browser-native `web_speech` (wasm32)
Codebase indexing + hybrid retrieval (vector + BM25) for the Brainwires Agent Framework. Includes AST-aware chunking via tree-sitter (12 languages), Git history search, and reranking via spectral diversity / cross-encoder.
Built-in concrete tools for the Brainwires Agent Framework — bash, file_ops, git, web, search, code_exec, semantic_search, browser, email, calendar, system. Built on `brainwires-tool-runtime`.
Tool execution runtime for the Brainwires Agent Framework — executor trait, registry, error taxonomy, sanitization, validation, transactions, smart router, plus optional orchestrator / OAuth / OpenAPI / sandbox / sessions / RAG-tool-search modules
The Brainwires Agent Framework — build any AI application in Rust
MCP server framework with middleware pipeline for the Brainwires Agent Framework
Model Context Protocol server with semantic tool matching, observation pipeline, and tiered inference for LegionIO
MCP-RB is a Ruby framework that provides a Sinatra-like DSL for implementing Model Context Protocol servers.
An MCP server that indexes Cute Framework header files and provides search functionality for structs, functions, enums, and other elements.
Plasma is a Ruby-based SDK that provides a Rails-inspired, convention-over-configuration approach to building Model Context Protocol servers.
A elegant and easy to use framework for building MCP servers with tools, resources, prompts, middleware, and more
A Ruby gem implementing the Model Context Protocol (MCP) server-side specification. Provides a framework for creating MCP servers that expose tools, resources, prompts, and roots to LLM clients with comprehensive security features, structured logging, and production-ready capabilities.
RobotLab is a Ruby framework for building and orchestrating multi-robot LLM workflows. Built on ruby_llm, it provides robots with template-based prompts, tools, and shared memory; networks for coordinating multiple robots with intelligent routing; MCP (Model Context Protocol) integration for external tool servers; and a memory system with Redis backend and semantic caching. Optional gems add Rails integration (robot_lab-rails), durable learning (robot_lab-durable), Ractor concurrency (robot_lab-ractor), and document storage (robot_lab-document_store).
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.