Click on "Deploy 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., "@metacall-mcp list my current deployments"
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.
A Model Context Protocol (MCP) server that exposes MetaCall FaaS operations as AI-callable tools, letting LLMs like Claude manage your MetaCall deployments directly.
This server wraps three MetaCall API endpoints as MCP tools:
Tool | Description | Underlying API |
| Lists all active FaaS deployments on your account |
|
| Calls a deployed function by name with arguments |
|
| Deploys a Git repository to MetaCall FaaS |
|
Related MCP server: Swagger MCP Adapter
Node.js ≥ 18
A MetaCall account with an API token
npm installExport your MetaCall API token as an environment variable before running:
export METACALL_TOKEN=your_token_hereYou can find your token in the MetaCall Dashboard under Settings → API Tokens.
npm run startOn success you'll see on stderr:
MetaCall MCP Server running...The server communicates over stdio, so Claude Desktop connects to it as a subprocess.
Add the following to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"metacall": {
"command": "npm",
"args": ["run", "start"],
"cwd": "/path/to/metacall-mcp",
"env": {
"METACALL_TOKEN": "your_token_here"
}
}
}
}Restart Claude Desktop and you'll see the MetaCall tools available in the tools panel.
list_deploymentsNo parameters. Returns a JSON array of all deployments on your account.
call_functionParameter | Type | Description |
| string | Deployment path/suffix (e.g. |
| string | Function name to call |
| array | Arguments to pass to the function |
deploy_from_repoParameter | Type | Description |
| string | Git repository URL |
| string? |
|
npm run build
# Output goes to ./dist/This server cannot be deployed
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
