Runtime

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools, data sources and workflows.

Runtime's MCP server gives an agent every Runtime product as tools, and it connects with one browser approval and no key to copy. Claude Code, Codex, Cursor, ChatGPT, VS Code and any client that speaks MCP can create sandboxes, run code, read files and fork machines through it (MCP).

Why it matters for AI agents

Before MCP, each AI application needed its own integration for each tool it used. MCP gives both sides one protocol: a tool is written once as an MCP server, and every MCP client can use it. The project's own description compares it to "a USB-C port for AI applications". Anthropic open-sourced it on 25 November 2024, and it is now supported by Claude, ChatGPT, Visual Studio Code, Cursor and many other clients.

MCP in facts

Fact Value
What it is An open protocol between LLM applications and external data and tools
Message format JSON-RPC 2.0, UTF-8 encoded
Roles Hosts (LLM applications), clients (connectors inside a host), servers
Server features Resources (context and data), prompts (templated messages), tools (functions)
Client features Elicitation: a server asks the user for more information
Transports stdio, to a client-launched subprocess; Streamable HTTP, to one endpoint
Latest revision 2026-07-28

Source: the MCP specification at modelcontextprotocol.io, read on 25 September 2026. The specification treats tools as arbitrary code execution and requires hosts to obtain the user's consent before invoking one.

Runtime's MCP server

Add it to Claude Code or Codex with one command:

Terminalclaude mcp add --scope user runtime -- npx -y withruntime mcpcodex mcp add runtime -- npx -y withruntime mcp

The first time, the server offers one tool, runtime_connect. The agent calls it and shows you a link and a code, you approve Connect agent in your browser, and every Runtime tool appears with nothing to restart. The command is a bridge: it forwards MCP messages to the remote server over the saved connection, so no key sits in the agent's configuration.

Clients that speak MCP over HTTP connect directly to https://api.withruntime.com/mcp over Streamable HTTP and sign in through the browser with OAuth 2.1 and PKCE (remote connection).

Tool What it does
runtime_sandbox_create Create a sandbox and wait until it is ready
runtime_sandbox_exec Run a command and get its exit code and output
runtime_sandbox_files_write Write a file into the sandbox
runtime_sandbox_interpreter_run A notebook-style session in Python, JavaScript, TypeScript and more
runtime_sandbox_fork Copies of a sandbox as it is now, with its memory and processes
runtime_sandbox_network_set Replace a sandbox's network rules
runtime_limits_get Whether this key is read-only, and its daily spending limit

Tool names read runtime_<product>_<verb>. The server sends instructions on first contact: the quick start, safe retries and how to report problems. The full list is in tools.

A sandbox can also run MCP servers of its own, such as GitHub, Postgres or a Playwright browser, at URLs your agent connects to (MCP servers in a sandbox).

Sources

Checked 25 September 2026.

Facts on this page were checked on 25 September 2026.

Claim 50 hours free