# Everything (MCP Server)

> Reference test server exercising every MCP protocol feature

- Type: MCP server
- Publisher: Model Context Protocol (official)
- Categories: Development
- Website: https://github.com/modelcontextprotocol/servers/tree/main/src/everything
- Source: https://github.com/modelcontextprotocol/servers
- Transport: stdio
- Launch command: npx -y @modelcontextprotocol/server-everything
- Sign-in: none
- GitHub stars: 90924
- Listed: 2024-11-25

## About

Reference/test server that implements prompts, tools, resources, sampling, elicitation, logging and more. Intended for developers building and testing MCP clients rather than end users.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add everything -- npx -y @modelcontextprotocol/server-everything
   ```

   config.toml:

   ```toml
   [mcp_servers.everything]
   command = "npx"
   args = ["-y", "@modelcontextprotocol/server-everything"]
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Everything",
       params={"command": "npx", "args": ["-y", "@modelcontextprotocol/server-everything"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Echo back 'hello world' using the echo tool")
       print(result.final_output)
   ```

## Tools

- `echo`
- `get-sum`
- `get-tiny-image`
- `get-annotated-message`
- `get-env`
- `get-resource-links`
- `get-structured-content`
- `trigger-long-running-operation`
- `trigger-sampling-request`
- `trigger-elicitation-request`
- `toggle-simulated-logging`
- `gzip-file-as-resource`

## Example prompts

- "Echo back 'hello world' using the echo tool"
- "Add 7 and 35 with get-sum"
- "Trigger a sampling request to test my client"
- "Start a long-running operation and show progress"

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/everything · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.