Welcome to Lunar.dev
Lunar.dev is an open-source platform for managing, governing and optimizing third-party API consumption across applications and AI agent workloads at scale.
Consumption Management for the AI Era
As AI agents and autonomous workflows increasingly rely on external APIs, there's a growing need for a mediation layer that acts as a central aggregation point between applications, agents, and the services they depend on.
Lunar.dev provides that layer—serving as a unified API Gateway for AI, delivering:
- Live API Traffic Visibility: Get real-time metrics on latency, errors, cost, and token usage across all outbound traffic, including LLM and agent calls.
- AI-Aware Policy Enforcement: Control tool access, throttle agent actions, and govern agentic traffic with fine-grained rules.
- Advanced Traffic Shaping: Apply rate limits, retries, priority queues, and circuit breakers to manage load and ensure reliability.
- Cost & Performance Optimization: Identify waste, smooth traffic peaks, and reduce overuse of costly APIs through smart gateway policies.
- Centralized MCP Aggregation: Streamline operations by consolidating multiple MCP servers into a single gateway, enhancing security, observability, and management.
Choose Your Path
Lunar.dev is composed of two major components:
- Lunar Proxy – our core API gateway and control layer
- Lunar MCPX – a zero-code aggregator for multiple MCP servers with unified API access
Explore the one that fits your needs—or use both for a full-stack solution.
Open Source at the Core
This project was born out of the need for a more robust, production-ready approach to managing third-party APIs. It remains open-source at its core and free for non-production/personal use. For production environments, we offer advanced features through guided onboarding and platform tiers; visit our website or reach out directly for more information
Recommend MCP Servers 💡
medadapt-content-server
A specialized Model Context Protocol (MCP) server for Claude Desktop that enhances AI-assisted medical learning by fetching and processing educational resources from PubMed, NCBI Bookshelf, and user-provided documents.
@effytech/freshdesk_mcp
An MCP server implementation that integrates with Freshdesk, enabling AI models to interact with Freshdesk modules and perform various support operations.
stitch-ai-mcp
MCP server implementation for Stitch AI's memory management system, providing tools for creating, retrieving, and managing AI agent memories.
builtwith
A Model Context Protocol (MCP) server that integrates with BuiltWith's technology detection API, allowing AI assistants to identify the technology stack behind any website through natural language commands.
gosset-ai/mcps
A collection of MCP servers for biomedical research offering access to PubMed, BioRxiv/MedRxiv, ClinicalTrials.gov, DrugBank, and OpenTargets databases.
asusevski/opendota-mcp-server
An MCP server for accessing OpenDota API data to get Dota 2 statistics, match, and player info for LLMs/AI assistants.