About Everpod
Everpod is a hosted service for running an AI agent on an always-on cloud computer, or having OpenClaw set up and run for the account owner. Its MCP server lets an existing agent inspect pods and start an OpenClaw or developer pod; payment and machine access remain outside its scope.
Key features
- 01List account pods
- 02Check pod status and links
- 03Start OpenClaw pods
- 04Start developer pods
- 05Bearer-key authentication
Use cases
- 01Start an OpenClaw pod from an agent
- 02Create a developer pod for an agent workflow
- 03Check whether a pod is ready or awaiting payment
MCP support
The hosted HTTP MCP server exposes tools to list pods, read a pod's status, and start a pod. A bearer key authorizes these account operations but cannot pay, change plans, delete pods, or access a developer pod's machine.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://everpod.ai/mcpclaude mcp add --transport http ai-everpod-everpod https://everpod.ai/mcp{"mcpServers":{"ai-everpod-everpod":{"type":"http","url":"https://everpod.ai/mcp"}}}Open in Cursor{"servers":{"ai-everpod-everpod":{"type":"http","url":"https://everpod.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-everpod-everpod":{"type":"http","url":"https://everpod.ai/mcp"}}}{"mcpServers":{"ai-everpod-everpod":{"serverUrl":"https://everpod.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://everpod.ai/mcpAuth requiredTools
Details
From the project READMEEverpod MCP server
Everpod puts your own AI agent on an always-on cloud computer, secured and backed up: run Claude Code, Codex or any agent you use on a machine that is yours, or have OpenClaw set up and run for you. 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 and start either kind of pod.
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, open your agent's control panel, or reach a developer pod's machine.
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_KEY
codex 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, starts a new agent or a developer pod for you, and prepares its own move 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:
{
"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.
Start an Everpod developer pod called atlas, with alex as my username, and tell me where to pay.
For a developer pod, the agent can take you from nothing to a machine you are logged in to; the steps that open the machine are yours. Get a developer pod with your agent has each step. For an agent that takes skills, the same steps are a skill, everpod-developer-pod, from github.com/everpod-ai/skills. Claude Code installs it with claude plugin marketplace add everpod-ai/skills and then claude plugin install everpod-developer-pod@everpod; Codex with codex plugin marketplace add everpod-ai/skills and then codex plugin add everpod-developer-pod@everpod. For another agent, copy its folder into the agent's skills folder.
Tools
list_pods: List the pods on the owner's Everpod account, oldest first. Each has its kind, 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, whether it is ready, and for a developer pod, which of its owner's steps to connect it are done.start_pod: Start a new pod for the owner: an OpenClaw pod, or with kind 'developer' a developer pod. 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, changed to the name and kind now asked for.
From code
The same three operations are REST routes, with client libraries for JavaScript and Python.
Questions
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.