Skip to content
aicoolies logo
Glama logo

Glama

MCP server directory and gateway

AI gateway and model management platform that provides a unified API for accessing multiple LLM providers (OpenAI, Anthropic, Google, Mistral, and more) through a single endpoint. Features model routing, cost tracking, usage analytics, rate limiting, and API key management across providers. Simplifies multi-provider AI integration by handling authentication, billing, and failover in one place. Useful for teams evaluating multiple models or building provider-agnostic AI applications.

About Glama

Glama is an all-in-one AI workspace, API gateway, and MCP hosting platform that provides unified access to over 100 AI models from multiple providers through a single interface with enterprise-grade security and compliance. It solves the challenge of managing multiple AI model subscriptions and MCP server deployments by consolidating everything into one platform where developers and teams can access models from OpenAI, Anthropic, Google, and others, compare responses side-by-side, and integrate MCP tools for extended capabilities. Glama combines the functionality of an AI chat interface, API gateway, and tool hosting platform into a comprehensive workspace for AI-powered workflows.

Glama provides an OpenAI-compatible API gateway with global load balancing and automatic failover across 100+ AI models, document processing for PDFs, Word files, and other formats with exact page references, and visualization capabilities using Mermaid diagrams and KaTex mathematical notation. The MCP hosting platform maintains a comprehensive, daily-updated registry of Model Context Protocol servers with deployment infrastructure for running MCP tools in production. Glama offers AES-256 encryption and SOC 2 compliance for enterprise security requirements, with team management features for collaborative AI workspaces.

Glama targets AI developers, enterprise teams, and organizations that need a unified platform for accessing multiple AI models, hosting MCP servers, and building AI-powered workflows with production-grade security and reliability. It integrates with the broader MCP ecosystem for tool discovery and deployment, while the API gateway provides a single endpoint for routing requests across dozens of model providers. Glama is particularly valuable for teams that need to evaluate and compare different AI models, manage MCP tool infrastructure, and enforce security policies across their AI operations from a single, centralized platform.

Pricing & Platform Specs

Pricing Summary

Freemium MCP discovery, browser-based inspection, and managed hosting platform. Free tier ($0) provides registry browsing, browser-based MCP Inspector sandboxing, and free deployment of open-source MCP servers. Starter plan starts at $9–$15/mo ($9 AI credits, 3 fast servers), Pro tier at $26–$49/mo ($26 AI credits, 10 fast servers, persistent storage), and Business at $80/mo (30 fast servers, 180-day log retention). Additional servers available at $2–$4/server/mo.

full pricing breakdown →

Supported Platforms

Web

Explore categories, tags & use cases

Categories

Public MCP server directory, now part of Arcade.dev

Smithery is a free public directory of Model Context Protocol (MCP) servers, owned by Arcade.dev since August 2026. Since October 31, 2026 it no longer hosts or proxies servers: its hosted server URLs, API, Connect, Toolbox, accounts, API keys, CLI and SDKs were shut down, and verified listings now point to each vendor's own MCP URL.

free

Community MCP server registry

Community-curated directory of Model Context Protocol (MCP) servers that extend AI assistants like Claude with real-world capabilities — file access, database queries, API integrations, browser control, and more. Lists servers organized by category (developer tools, data, productivity) with installation instructions and compatibility info. Helps developers discover and connect MCP servers to their AI workflows. Essential resource for the growing MCP ecosystem.

freeOpen Source

Hosted MCP server platform

Platform for running MCP servers securely in WebAssembly sandboxes. One-click install for Claude Desktop, VS Code, and other MCP-compatible clients with no Docker required. Simplifies MCP server deployment and management by handling isolation, security, and distribution, making it easy to extend AI assistants with custom tools without infrastructure overhead.

freemiumOpen Source

Side-by-Side Comparisons

MCP Registry parent MCP protocol mark
MCP Registry
vs
Glama logo
Glama

MCP Registry vs Glama: Official publishing authority or richer MCP discovery marketplace?

MCP Registry and Glama overlap at the point where developers look for MCP servers, but they serve different jobs. The official MCP Registry is the vendor-neutral publication and synchronization layer: it assigns canonical server names, verifies namespace ownership, validates package metadata, and exposes a stable API for downstream registries. Glama consumes that ecosystem data and adds human search, tool-level schemas, quality and health signals, sandbox analysis, deployment, gateway, logs, and access controls. Publishers should use the official Registry to establish identity and release metadata. Teams choosing, testing, and operating servers will usually get more practical value from Glama, so Glama is the overall winner for this buyer-focused comparison.

Composio logo
Composio
vs
Glama logo
Glama

Composio vs Glama: Managed Agent Actions or MCP Registry Intelligence?

Composio and Glama both simplify MCP adoption, but they solve different layers of the stack. Composio gives agents managed, per-user access to more than 1,000 app toolkits through sessions, seven discovery-and-execution meta-tools, and hosted authentication; Glama emphasizes a large continuously analyzed registry, tool-level search, inspection, gateway controls, and server hosting. Composio stands out as the primary recommendation for teams whose primary goal is reliable cross-app action rather than ecosystem discovery.

Smithery logo
Smithery
vs
Glama logo
Glama

Smithery vs Glama: Which MCP Server Directory Should You Use?

Smithery and Glama are now both MCP server directories. Glama's registry lists more than 115,000 servers with license, quality and maintenance grades. Smithery, owned by Arcade.dev, became a curated, non-proxied directory on October 31, 2026, after shutting down hosting, its API and its CLI. For finding and screening servers, Glama is the more useful directory.

Community experience

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is Glama?

AI gateway and model management platform that provides a unified API for accessing multiple LLM providers (OpenAI, Anthropic, Google, Mistral, and more) through a single endpoint. Features model routing, cost tracking, usage analytics, rate limiting, and API key management across providers. Simplifies multi-provider AI integration by handling authentication, billing, and failover in one place. Useful for teams evaluating multiple models or building provider-agnostic AI applications.

Is Glama free?

Glama offers a free tier alongside paid plans. Freemium MCP discovery, browser-based inspection, and managed hosting platform. Free tier ($0) provides registry browsing, browser-based MCP Inspector sandboxing, and free deployment of open-source MCP servers. Starter plan starts at $9–$15/mo ($9 AI credits, 3 fast servers), Pro tier at $26–$49/mo ($26 AI credits, 10 fast servers, persistent storage), and Business at $80/mo (30 fast servers, 180-day log retention). Additional servers available at $2–$4/server/mo.

Is Glama still maintained?

Yes — Glama is active. Its listing was last verified on September 6, 2026.

What are the best Glama alternatives?

The first editor-selected Glama alternatives are Smithery, MCP Servers Directory, mcp.run.