Metorial
🎖️ 📇 ☁️ Connect AI agents to 600+ integrations with a single interface - OAuth, scaling, and monitoring included
What is Metorial?
Metorial is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🎖️ 📇 ☁️ connect ai agents to 600+ integrations with a single interface - oauth, scaling, and monitoring included
🎖️ 📇 ☁️ Connect AI agents to 600+ integrations with a single interface - OAuth, scaling, and monitoring included
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🎖️ 📇 ☁️ Connect AI agents to 600+ integrations with a single
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx metorialConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Metorial
Metorial is an identity and access control layer that connects AI agents to over 1,200 SaaS and enterprise integrations through a single unified interface, handling OAuth flows, API key management, RBAC permissions, SAML SSO, and audit logging automatically. Rather than hardcoding credentials into each agent, developers create provider deployments through the Metorial dashboard and then expose those integrations as MCP tools at runtime. This makes it straightforward to build secure multi-tenant AI agents that can act on Slack, GitHub, Salesforce, and hundreds of other platforms without managing authentication infrastructure.
Prerequisites
- Node.js 18+ or Python 3.9+ depending on your chosen SDK
- A Metorial account with a valid METORIAL_API_KEY from the dashboard
- At least one provider deployment configured in the Metorial dashboard (e.g., Slack, GitHub)
- An MCP-compatible client such as Claude Desktop or a compatible agent framework (Anthropic SDK, Vercel AI SDK, PydanticAI)
- Docker if deploying the Metorial container in a self-hosted environment
Create a Metorial account and configure a provider
Sign up at metorial.com, create a provider deployment for the integration you want (e.g., Slack or GitHub), and complete any required OAuth setup. Copy your METORIAL_API_KEY from account settings.
Install the Metorial SDK
Add the Metorial package and your chosen AI framework SDK to your project.
# Node.js / TypeScript
npm install metorial @metorial/ai-sdk @ai-sdk/anthropic ai
# Python
pip install metorial pydantic-ai python-dotenvInitialize a Metorial session and expose tools
In your agent code, create a Metorial client, open a session for the desired provider deployment, and pass the session tools to your AI framework. The session handles authentication automatically.
import Metorial from 'metorial';
const metorial = new Metorial({ apiKey: process.env.METORIAL_API_KEY });
const deployment = await metorial.providerDeployments.create({
providerId: 'slack'
});
const session = await metorial.connect(deployment.id);
const tools = await session.tools(); // pass to your AI frameworkConfigure Claude Desktop to use the Metorial MCP server
Add the Metorial server to your claude_desktop_config.json. The METORIAL_API_KEY env var is the only required credential.
{
"mcpServers": {
"metorial": {
"command": "npx",
"args": ["metorial"],
"env": {
"METORIAL_API_KEY": "your_metorial_api_key"
}
}
}
}Handle OAuth setup sessions for end users
When an integration requires user-level OAuth (e.g., connecting a user's personal Slack account), create a setup session and direct the user to the returned URL to complete authorization.
const setupSession = await metorial.providerDeployments.setupSessions.create(deployment.id);
const authUrl = setupSession.url; // redirect user here
await metorial.waitForSetupSession(setupSession.id);Metorial Examples
Client configuration
Claude Desktop configuration for the Metorial MCP server with the required API key.
{
"mcpServers": {
"metorial": {
"command": "npx",
"args": ["metorial"],
"env": {
"METORIAL_API_KEY": "your_metorial_api_key"
}
}
}
}Prompts to try
Once connected through Metorial, these prompts exercise the integrations you have configured.
- "Send a Slack message to the #general channel saying the deployment is complete"
- "Create a GitHub issue in my-org/my-repo titled 'Fix login bug' with the label 'bug'"
- "Search the web for the latest AI agent frameworks and summarize the top results"
- "List all open Salesforce opportunities assigned to me"
- "Post a message to our Discord server's announcements channel"Troubleshooting Metorial
All tool calls fail with an authentication error referencing METORIAL_API_KEY
Verify that the METORIAL_API_KEY environment variable is correctly set in your config and that the key has not been revoked. Generate a new key from the Metorial dashboard if needed.
OAuth integrations return 'setup required' errors when the agent tries to use them
The end user needs to complete the OAuth flow. Create a setup session (providerDeployments.setupSessions.create), direct the user to the returned URL, and call waitForSetupSession before attempting tool calls.
The npx metorial command hangs or fails with a module resolution error
The package may not yet be on npm. Install it explicitly with npm install -g metorial first, or use the Docker image from the metorial/metorial repository with docker compose up.
Frequently Asked Questions about Metorial
What is Metorial?
Metorial is a Model Context Protocol (MCP) server that 🎖️ 📇 ☁️ connect ai agents to 600+ integrations with a single interface - oauth, scaling, and monitoring included It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Metorial?
Follow the installation instructions on the Metorial GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Metorial?
Metorial works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Metorial free to use?
Yes, Metorial is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Metorial Alternatives — Similar Business Applications Servers
Looking for alternatives to Metorial? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Metorial in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Metorial?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.