Free-AI Gateway MCP Server
Provides integration with Cloudflare Workers AI for image generation and embedding.
Uses Fastify as the HTTP server framework for the OpenAI-compatible proxy gateway.
Provides integration with Google Cloud Platform for translation, speech-to-text, text-to-speech, and vision services.
Provides integration with Hugging Face for text generation, tool calling, and image generation.
Provides integration with NVIDIA NIM for text generation, tool calling, reasoning, vision, embedding, reranking, and moderation.
Provides an OpenAI-compatible HTTP proxy endpoint for chat completions and other AI services.
Provides observability integration through a typed event bus, supporting OpenTelemetry for lifecycle events.
Provides observability integration through a typed event bus, supporting Prometheus for lifecycle events.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Free-AI Gateway MCP Servergenerate a response explaining quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
⚡ Free-AI Gateway
Enterprise-grade capability-routed AI Gateway monorepo aggregating free-tier and local AI APIs into reusable libraries, Model Context Protocol (MCP) servers, and OpenAI-compatible HTTP proxies.
📚 New to Free-AI Gateway? Check out the comprehensive Architecture & Developer Guide (LEARN.md) for detailed deep dives, tutorials, and integration patterns.
📖 Architecture & Monorepo Overview
free-ai-gateway is organized as an enterprise monorepo separating pure AI orchestration infrastructure from protocol-specific delivery mechanisms (HTTP Fastify Proxy, MCP Server, CLI, & Web Examples):
flowchart TD
subgraph CoreLayer ["@free-ai-gateway/core (Standalone npm package)"]
Router["CapabilityRouter & Strategy Engine"]
Providers["20 Provider Adapters & Dynamic Registry"]
Resilience["QuotaTracker & CircuitBreaker"]
Observability["EventBus & MetricsTracker"]
Transport["HttpClient with Exponential Backoff"]
end
subgraph Consumers ["Consumer Applications & Examples"]
GatewayApp["apps/gateway (@free-ai-gateway/gateway)<br/>Fastify HTTP OpenAI Proxy & SSE Streamer"]
McpApp["packages/mcp (@free-ai-gateway/mcp)<br/>Model Context Protocol Server"]
SkillsPkg["packages/skills (@free-ai-gateway/skills)<br/>Agentic IDE Skills & CLI"]
CliApp["packages/cli (@free-ai-gateway/cli)<br/>Terminal Assistant & Diagnostics"]
NextApp["examples/nextjs-chat<br/>Next.js 14+ Fullstack Streaming UI"]
Collections["examples/collections<br/>Postman & Bruno API Test Suites"]
end
GatewayApp -->|consumes| CoreLayer
McpApp -->|consumes| CoreLayer
SkillsPkg -->|integrates with| CoreLayer
CliApp -->|consumes| CoreLayer
NextApp -->|proxies to| GatewayApp
Collections -->|tests| GatewayAppMonorepo Workspaces Matrix
Package / App | Location | Purpose | Dependencies |
|
| Protocol-neutral capability router, resilience engine, and 20 provider adapters. |
|
|
| Model Context Protocol server exposing capability tools to AI agents (Claude Desktop, Cursor). |
|
|
| Agentic IDE skills ( | Standalone CLI & API |
|
| Terminal AI assistant, interactive chat REPL, model catalog, and diagnostics tool. |
|
|
| High-throughput Fastify HTTP proxy serving OpenAI-compatible endpoints with auto-discovery and SSE. |
|
|
| Fullstack Next.js 14+ App Router demo with Vercel AI SDK & zero-dep native SSE streams. |
|
|
| Complete Postman v2.1 and Bruno collections covering all 19 API endpoints. | Standard JSON / |
Related MCP server: agentforge
✨ Key Capabilities
🎯 Capability-Based Routing: Request what you need (
model: "auto:tool_calling+structured_output"), and let the router choose the fastest healthy free provider.📐 Strategy Pattern Engine: Pluggable load balancing strategies (
AdaptiveHealthStrategy,LowestLatencyStrategy, or customIRoutingStrategy).🔄 Autonomous Failover: Transparently cycles through ranked candidate providers until success upon encountering upstream
429(Rate Limit) or5xxerrors.🛡️ Circuit Breaker: Detects failing providers and enters exponential cooldown backoff to prevent cascade failures.
⏱️ Sliding-Window Quota Tracking: In-memory accounting of RPM, TPM, and RPD with proactive limit protection.
🔑 Multi-Key Pool Rotation: Configure comma-separated API keys (
PROVIDER_KEY=k1,k2,k3) with round-robin rotation and per-key rate-limit isolation.🔌 Dynamic Provider Autoloader: Add new providers by dropping a class extending
BaseProviderintopackages/core/src/providers/.📡 Typed Event Bus & Observability: Lifecycle events for OpenTelemetry and zero-overhead Prometheus
/metricsendpoint.🤖 Model Context Protocol (MCP) Ready: Use directly in Claude Desktop, Cursor, or agent workflows.
🧩 Supported Providers Matrix (20 Adapters)
Provider | Modalities / Capabilities | Authentication | Limit Scope |
Google AI Studio |
|
| Per Model |
Groq |
|
| Account |
Ollama (Local) |
| None (Local Daemon) | Local Node |
SambaNova Cloud |
|
| Account |
NVIDIA NIM |
|
| Account |
Cohere |
|
| Account |
OpenRouter |
|
| Account |
OpenCode Zen |
|
| Account |
Bazaarlink.ai |
|
| Account |
aimlapi.com |
|
| Account |
OVHcloud AI |
|
| Per Model |
Voyage AI |
|
| Account |
Jina AI |
|
| Account |
Hugging Face |
|
| Shared Pool |
Cloudflare Workers AI |
|
| Shared Pool |
Google Cloud Platform |
|
| Account |
MyMemory |
|
| Account |
Unstructured.io |
|
| Account |
Exa AI |
|
| Account |
Tavily |
|
| Account |
🚀 Quick Start
1. Installation
# Clone the repository
git clone https://github.com/zaber-dev/free-ai-gateway.git
cd free-ai-gateway
# Install dependencies across all monorepo workspaces
npm install2. Configure Environment
Copy .env.example to .env and provide keys for the providers you wish to enable:
cp .env.example .envPORT=3000
GROQ_API_KEY=gsk_...
GOOGLE_API_KEY=AIza...
NVIDIA_API_KEY=nvapi-...
COHERE_API_KEY=...3. Build & Run
# Compile all workspace packages
npm run build
# Run all 55 automated tests across all packages
npm test
# Start the Fastify HTTP Gateway (Dev mode)
npm run dev
# Start the Gateway in Production
npm start💻 Usage Modalities
Option A: HTTP Gateway (OpenAI Compatible)
Call the local proxy with any OpenAI SDK or curl:
curl http://localhost:3000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "auto:tool_calling+structured_output",
"messages": [
{ "role": "user", "content": "Extract name and age from: Alice is 30 years old." }
]
}'import OpenAI from "openai";
const client = new OpenAI({
baseURL: "http://localhost:3000/v1",
apiKey: "not-needed",
});
const completion = await client.chat.completions.create({
model: "auto:reasoning",
messages: [{ role: "user", content: "Solve: How many r's in strawberry?" }],
});
console.log(completion.choices[0].message.content);Option B: Embedding @free-ai-gateway/core as a TypeScript Library
Embed the capability router directly into your application without launching an HTTP server:
import {
CapabilityRouter,
Registry,
QuotaTracker,
CircuitBreaker,
EventBus,
LowestLatencyStrategy,
} from "@free-ai-gateway/core";
const registry = new Registry();
const quota = new QuotaTracker();
const breaker = new CircuitBreaker();
const eventBus = new EventBus();
// Listen to lifecycle telemetry
eventBus.on("request:fallback", (evt) => {
console.warn(`[Fallback] Failed on ${evt.attemptedProvider}: ${evt.error}`);
});
const router = new CapabilityRouter(
registry,
quota,
breaker,
undefined,
eventBus,
new LowestLatencyStrategy()
);
const response = await router.route({
capabilities: ["text", "tool_calling"],
payload: {
messages: [{ role: "user", content: "Hello AI!" }],
},
});
console.log("Served by:", response.servedBy);
console.log("Data:", response.data);Option C: Model Context Protocol (MCP) Server
Connect Free-AI Gateway to Claude Desktop or Cursor:
{
"mcpServers": {
"free-ai-gateway": {
"command": "node",
"args": ["/path/to/free-ai-gateway/packages/mcp/dist/index.js"],
"env": {
"GROQ_API_KEY": "gsk_...",
"GOOGLE_API_KEY": "AIza..."
}
}
}
}Exposed MCP Tools:
freeai_generate: Generate text, reasoning, or code with automatic failover.freeai_search: Web search queries via Exa / Tavily.freeai_embed: Generate vector embeddings via Voyage, Jina, Gemini.freeai_rerank: Rerank documents for retrieval augmented generation (RAG).freeai_analyze_image: Multimodal vision analysis.
Option D: Agentic IDE Skills (@free-ai-gateway/skills)
Install Free-AI Gateway agent skills directly into your IDE or autonomous coding assistant:
# Install to Google Antigravity (.agents/skills)
npx @free-ai-gateway/skills install --target=antigravity
# Install to Cursor (.cursor/skills)
npx @free-ai-gateway/skills install --target=cursor
# Install to Claude Code (.claude/skills)
npx @free-ai-gateway/skills install --target=claude
# Install to all supported AI assistants
npx @free-ai-gateway/skills install --target=allOption E: Terminal CLI Tool (@free-ai-gateway/cli)
Use Free-AI directly from your terminal or command-line scripts:
# One-off prompt execution with auto-routing
npx @free-ai-gateway/cli "Explain MapReduce in simple terms"
# Interactive chat REPL in terminal
npx @free-ai-gateway/cli chat --capability=reasoning
# Check model catalog with formatting & capability filter
npx @free-ai-gateway/cli models --format=markdown --capability=code
# Run system diagnostics
npx @free-ai-gateway/cli doctor🏛️ Monorepo Structure
free-ai-gateway/
├── packages/
│ ├── core/ # @free-ai-gateway/core
│ │ ├── AGENTS.md # Agentic guidelines for @free-ai-gateway/core
│ │ ├── src/
│ │ │ ├── capabilities/ # Capability definitions & parsing
│ │ │ ├── config/ # providers.json, schema, config sources
│ │ │ ├── errors/ # ProviderError, NoProviderAvailableError
│ │ │ ├── observability/ # EventBus, MetricsTracker
│ │ │ ├── providers/ # 20 Provider Adapters + Registry + Loader
│ │ │ ├── resilience/ # QuotaTracker, CircuitBreaker
│ │ │ ├── router/ # CapabilityRouter & Strategy Pattern
│ │ │ ├── transport/ # HttpClient with exponential backoff
│ │ │ ├── types/ # Unified contracts & response schemas
│ │ │ └── index.ts # Public Core API
│ │ ├── tests/ # 28 Core unit tests
│ │ └── package.json
│ │
│ ├── mcp/ # @free-ai-gateway/mcp
│ │ ├── AGENTS.md # Agentic guidelines for @free-ai-gateway/mcp
│ │ ├── src/
│ │ │ ├── tools/ # generate, search, embed, rerank, analyze-image
│ │ │ ├── resources/ # capabilities, models catalog
│ │ │ ├── server.ts # FreeAiMcpServer handler
│ │ │ └── index.ts
│ │ ├── tests/ # 3 MCP server tests
│ │ └── package.json
│ │
│ ├── skills/ # @free-ai-gateway/skills
│ │ ├── AGENTS.md # Agentic guidelines for @free-ai-gateway/skills
│ │ ├── src/
│ │ │ ├── skills/ # Built-in skills (free-ai-gateway, scaffolding, mcp)
│ │ │ ├── installer.ts # Multi-target installer
│ │ │ ├── cli.ts # CLI executable (free-ai-skills)
│ │ │ └── index.ts
│ │ ├── tests/ # 4 Skills tests
│ │ └── package.json
│ │
│ └── cli/ # @free-ai-gateway/cli
│ ├── AGENTS.md # Agentic guidelines for @free-ai-gateway/cli
│ ├── src/
│ │ ├── commands/ # prompt, chat, models, doctor, skills
│ │ ├── cli.ts # Argument parsing & dispatcher
│ │ ├── bin.ts # CLI executable (free-ai, freeai)
│ │ └── index.ts
│ ├── tests/ # 8 CLI tests
│ └── package.json
│
├── apps/
│ └── gateway/ # @free-ai-gateway/gateway (HTTP App)
│ ├── AGENTS.md # Agentic guidelines for @free-ai-gateway/gateway
│ ├── src/
│ │ ├── adapters/ # OpenAI chat response normalizer & SSE chunker
│ │ ├── api/
│ │ │ ├── routes/ # Fastify route modules & RouteLoader
│ │ │ └── server.ts # Server factory, timing hooks, 404 handler
│ │ ├── jobs/ # Background JobScheduler & reverify worker
│ │ └── index.ts
│ ├── tests/ # 7 Gateway HTTP tests
│ ├── Dockerfile # Monorepo container builder
│ └── package.json
│
├── examples/
│ ├── nextjs-chat/ # Next.js 14+ App Router & Vercel AI SDK example
│ └── collections/ # Ready-to-import Postman & Bruno API suites
│
├── tests/
│ └── e2e/ # 5 Cross-package E2E integration tests
│
├── AGENTS.md # Monorepo Root Agentic Guidelines
├── CLAUDE.md # Claude Code Instructions
├── .agents/ # Workspace Skills Directory
├── .github/workflows/ci.yml # Matrix CI workflow
├── docker-compose.yml
├── package.json # Root workspace definition
├── tsconfig.base.json # Shared TypeScript compiler settings
└── README.md🤝 Community & Governance
📖 Architecture Blueprint: Deep dive into the internal system design and data flow.
🎓 Developer & Learning Guide: Tutorials, programmatic usage, and SDK patterns.
🗺️ Product Roadmap: Planned milestones, distributed state, and upcoming features.
💬 Support Guide: Troubleshooting, community discussions, and help channels.
🏛️ Project Governance: Decision-making process, maintainer roles, and release policies.
✍️ Contributing Guide: Step-by-step instructions for adding new provider adapters.
🔒 Security Policy: Vulnerability disclosure guidelines.
📜 Code of Conduct: Community standards and expectations.
👤 Author
Created and maintained with ❤️ by Md. Mahedi Zaman Zaber.
📄 License
This project is open source and available under the MIT License.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMulti-tool MCP server for AI agents with 29 tools across web scraping, SEO analysis, screenshot and PDF generation, domain intelligence, content extraction, multi-chain EVM blockchain queries, and security toolkit. Free tier available with no auth required.221MIT
- FlicenseAqualityFmaintenanceMCP server that exposes 300+ AI agents as tools via a single API key. Supports listing agents, invoking any agent with chat-completion style messages, checking agent health, and retrieving platform statistics.53-
- AlicenseNot gradedqualityCmaintenanceA unified MCP server providing AI agents with 40+ developer APIs including geolocation, crypto prices, DNS lookup, and web scraping. Enables natural language access to various tools through a single gateway.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access a unified catalog of tools from various APIs (OpenAPI, GraphQL, MCP, Google Discovery) through the MCP protocol.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zaber-dev/free-ai-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server