Everpod

ai.everpodv0.1.0Updated Oct 4, 2026

Managed hosting for open-source AI agents: see your pods and start a new one from your own agent.

VerifiedStreamable HTTPWeb executableAI & MLCloud & InfrastructureBusiness & Commerce

Overview

AI-generated overview

Lets an assistant list your Everpod pods, check their status and payment links, and start a new pod for you.

What it does
Everpod's hosted MCP server exposes three operations: list_pods lists the pods on your account oldest first with status and the link you need, get_pod reads one pod by id to check whether it has been paid for and is ready, and start_pod starts a new pod under a name you choose. Starting a pod charges nothing at the time of the call; the pod stays unpaid until you open its pay_url in a browser and pay there. While an unpaid pod exists, calling start_pod again returns that same pod, renamed if the name differs.
When to use it
Use it when you already run an agent such as Claude Code or Codex and want that agent to see your Everpod pods or start a new one for you without leaving the chat. It is a thin account-management layer, not a way to control or configure the agent running on the pod.
Requirements
A remote HTTP endpoint at nothing to install or run locally. You need an Everpod account (signing in with an emailed code creates one) and an API key made at everpod.ai/account/keys, sent as the header Authorization: Bearer YOUR_KEY. Clients can read the key from an environment variable such as EVERPOD_API_KEY.
Before you install
The Authorization header carries an API key that lets a trusted agent or app see your pods and start new ones, so keep it out of shared files and prefer reading it from an environment variable. Starting a pod creates a billable resource: the call itself charges nothing, but the pod stays unpaid until you open pay_url and pay, and you pay on everpod.ai. The server cannot pay, change or cancel a plan, delete anything, or open the agent's control panel.

Installation

In SourceWeft

  1. Open Everpod in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "everpod": {
      "type": "http",
      "url": "https://everpod.ai/mcp"
    }
  }
}

README

Everpod MCP server

Everpod runs an AI agent on a pod: a private, always-on cloud computer of its own. This is Everpod's MCP server, for an agent you already use, such as Claude Code or Codex, to work with your Everpod account for you.

A key lets an agent or an app you trust see your pods and start a new one for you, which you then pay for on everpod.ai. It can't pay, change or cancel a plan, delete anything, or open your agent's control panel.

The server is hosted at https://everpod.ai/mcp. There is nothing to install or run. The full reference is at everpod.ai/docs/api.

Connect

To make a key, open everpod.ai/account/keys and sign in with your email address and the code we send you. If you have no account yet, signing in makes one. An MCP client connects to https://everpod.ai/mcp over HTTP and sends the key as the header Authorization: Bearer YOUR_KEY.

Claude Code

claude mcp add --transport http --scope user everpod https://everpod.ai/mcp \  --header "Authorization: Bearer YOUR_KEY"

Codex

export EVERPOD_API_KEY=YOUR_KEYcodex mcp add everpod --url https://everpod.ai/mcp \  --bearer-token-env-var EVERPOD_API_KEY

OpenClaw

openclaw mcp set everpod '{"url": "https://everpod.ai/mcp",  "transport": "streamable-http",  "headers": {"Authorization": "Bearer YOUR_KEY"}}'

An OpenClaw agent can run this itself, and has the tools from its next message. Or install the Everpod skill from ClawHub, and the agent connects itself and can move itself onto a pod: openclaw skills install @everpod/everpod.

Another MCP client

Give it the address and the header. As a JSON entry, in the form Claude Code's .mcp.json takes, with the key read from an environment variable so that it is never written into a file you share:

json
{  "mcpServers": {    "everpod": {      "type": "http",      "url": "https://everpod.ai/mcp",      "headers": { "Authorization": "Bearer ${EVERPOD_API_KEY}" }    }  }}

Then ask the agent, for example:

Start an Everpod pod called Otto and tell me where to pay.

Tools

  • list_pods: List the pods on the owner's Everpod account, oldest first. Each has its status and the link its owner needs: pay_url while it is awaiting payment, url (the pod's page on everpod.ai) once it is paid.
  • get_pod: Read one pod by its id: its status and the link its owner needs. This is how to check whether a started pod has been paid for, and whether it is ready.
  • start_pod: Start a new pod for the owner, under the name they want for their agent. This call charges nothing: the pod stays unpaid until its owner opens pay_url in their browser and pays there. While the account has an unpaid pod, calling again returns that same pod, renamed if the name differs.

From code

The same three operations are REST routes, with client libraries for JavaScript and Python.

Questions

[email protected]

Source: README.md at commit 145ffa5

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 4, 2026