Open Source TypeScript MCP Gateways

Unla is a lightweight, highly available MCP gateway written in Go that turns existing MCP servers or ordinary HTTP APIs into MCP-compliant services through configuration, not code changes. Its goal is to let teams “wire up” tools they already run—internal REST endpoints, third-party APIs, or local MCP servers—and present a single, reliable MCP interface to clients like Claude Desktop, Cursor, and IDEs. The gateway focuses on operational concerns you’d expect in production: multi-instance availability, health checking, and declarative routing that maps upstreams to MCP tools and resources. A quick-start and CLI make it easy to stand up an API server, while the package structure exposes helpers for people who want to embed or extend the gateway. Because it is itself MCP-speaking, Unla can sit in front of mixed fleets and normalize transports and schemas for clients. Documentation and pkg.go.dev pages reinforce the positioning as a stable, Go-native building block for MCP deployments.

MCP Konnect is a Model Context Protocol (MCP) server implementation that enables AI assistants and agents to interact with Kong Konnect, the API management and gateway platform from Kong. This server exposes Kong Konnect’s APIs through standardized MCP interfaces so that tools like conversational AI or agent systems can query analytics, inspect configuration, and manage Kong Gateway resources using natural language or programmable agents. By bridging MCP clients to Kong’s control plane, the project allows autonomous agents to retrieve data on traffic metrics, route definitions, services, plugins, and consumer settings without writing custom API integration code. It also groups tools into categories—such as analytics, configuration, and control plane management—to organize capabilities logically for AI workflows.

Peta Core is an open-source project that aims to provide foundational infrastructure for building extensible, distributed applications and services, particularly in the context of agentic systems and modern tooling. It typically encompasses core abstractions, protocols, and utilities that other modules in the PETA ecosystem can build upon, offering patterns for service discovery, messaging, workflow orchestration, and plugin integration. PETA-Core may include frameworks for managing agent lifecycles, standard interfaces for connectors, and support for consistent configuration across components, making it easier to assemble complex, multi-part applications with clear boundaries and reusable logic. The project’s core role is to reduce integration friction for developers by establishing conventions and shared libraries that accelerate development in distributed, AI-augmented contexts.

DeployStack is an open-source framework that helps developers and teams define and deploy production infrastructure stacks using modular, reusable templates, often with IaC (infrastructure as code) principles. It provides a structured way to compose resources such as cloud networking, compute, and managed services into coherent deployment blueprints that can be versioned and reused across projects. By abstracting common deployment patterns and capturing them as templates, Deploystack reduces duplication of effort that typically occurs when setting up stacks for different applications or environments. The project emphasizes repeatability and clarity, enabling teams to follow best practices for scalability, security, and operational reliability without hand-crafting deployment scripts for every new service. It supports integration with popular cloud providers and infrastructure tooling, streamlining workflows that span local development through staging and production environments.

Gate22 is an open-source governance and control plane for Model Context Protocol (MCP) environments that helps teams define and enforce policies about which tools and capabilities AI agents can access, how they can interact with those tools, and how usage is logged and audited. It provides a centralized layer where organizations can configure permission boundaries, role-based access, and operational constraints that govern agent behavior and tool invocation across agentic IDEs or custom agent stacks. By integrating with MCP-aware systems, Gate22 helps maintain security and compliance while enabling teams to scale agent-enabled workflows without losing observability into what actions are taken and why. It can be used to enforce fine-grained policies that restrict dangerous or unauthorized operations, track which agents are calling which tools, and record metadata for auditing and debugging.

MetaMCP is an all-in-one MCP aggregator, orchestrator, and middleware that merges many MCP servers into a single, policy-aware server you can point any MCP client at. It’s built to centralize discovery, apply middlewares (e.g., auth, rate limits, transforms), and present a unified catalog of tools and resources from diverse backends. The repository and site describe it as “the one MCP to manage all your MCPs,” with diagrams and examples showing how to compose fleets behind a single endpoint. It ships Dockerized for quick deployment and emphasizes dynamic aggregation so teams can register or remove servers without restarting clients. The org maintains related repos and a GUI app for cloud and self-hosted setups, with a note that the cloud demo is outdated while the open-source v2 evolves. Overall, MetaMCP aims to simplify multi-server MCP operations for individuals and organizations.

Portkey AI Gateway aims to offer a blazing fast, secure, and flexible gateway for interacting with a wide variety of models and enforcing guardrails. It presents a single, friendly API through which you can route to 200+ LLMs, while applying configurable input/output guardrails to enforce policies or restrict certain content. It supports automatic retries, fallbacks, load balancing across providers or keys, and request timeouts to avoid latency spikes. The gateway is multimodal: it can handle text, vision, audio, and image models under a common interface. It also offers features for governance: role-based access, compliance with standards (SOC2, HIPAA, GDPR), secure key management, and logging/analytics of usage, latency, errors, and cost. The system integrates with agent frameworks like LangChain, Autogen, and others, enabling the building of more complex AI applications. It’s lightweight and optimized for low latency with a small footprint.