A local Model Context Protocol server that demonstrates and tests the protocol's available features. Model Context Protocol is a standard way for AI applications to connect to tools and data.

Use it to test MCP clients, integrations, and protocol behavior during development.

It gives developers a controlled service for checking whether an MCP client handles different protocol features correctly.

everything — MCP server by rivet-dev/sandbox-agent

About the project

sandbox-agent is an HTTP and server-sent-events service that runs coding agents inside isolated sandboxes and lets another application control them remotely. Developers use it to run agents such as Claude Code, Codex, OpenCode, Cursor, Amp, or Pi while streaming events, managing sessions, and storing transcripts. The catalogue entries provide agents, skills, commands, instructions, and MCP integration for working with the service.

rivet-dev/sandbox-agent · 1,609 stars · on GitHub · sandboxagent.dev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/rivet-dev/sandbox-agent

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/rivet-dev/sandbox-agent/everything/github.svg)](https://agentmods.dev/mcp/rivet-dev/sandbox-agent/everything)

Your own site

<a href="https://agentmods.dev/mcp/rivet-dev/sandbox-agent/everything"><img src="https://agentmods.dev/badge/mcp/rivet-dev/sandbox-agent/everything/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/rivet-dev/sandbox-agent/everything"><img src="https://agentmods.dev/badge/mcp/rivet-dev/sandbox-agent/everything.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

everything scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 8 lines

What it actually says

{
  "everything": {
    "args": [
      "@modelcontextprotocol/server-everything"
    ],
    "command": "npx"
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 8 lines scan A a2041e967de9

Subscribe to this mod's changes

everything is an MCP server published in the GitHub repository rivet-dev/sandbox-agent (1,609 stars, last pushed 4d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code agent ai amp claude codex

salva

MCP server "salva" as configured in 0xRyanlee/salva. Runs apps.mcp with /Volumes/Astoria/Projects/salva/.venv/bin/python.

0xRyanlee/salva · not measured

rea

Reverse engineer anything from your terminal or agent with one CLI and MCP server. Runs locally from the rea-agents npm package.

morluto/rea · not measured

bls-mcp

MCP server "bls-mcp", hosted remotely at 127.0.0.1, as configured in openai/openai-cookbook.

openai/openai-cookbook · not measured

mcp-search

MCP server "mcp-search" as configured in thedotmack/claude-mem. Runs const f=require('fs'),p=require('path'),o=require('os');const h=o.homedir();const C=process.env.CLAUDE_CONFIG_DIR||p.join(h,'.claude');const E=process.env.CLAUDE_PLUGIN_ROOT||process.env.PLUGIN_ROOT||'';const d=process.cwd();const S=n=>{const…

thedotmack/claude-mem · not measured

claude-flow

Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code. Runs locally from the @claude-flow/cli npm package. Needs 6 environment variables to run.

ruvnet/RuView · not measured

engine_mcp

MCP server "enginemcp" as configured in flutter/flutter. Launched with dart run tools/mcp/bin/main.dart.

flutter/flutter · not measured