Exec Sandbox MCP Server

Exec Sandbox MCP server exists for a simple reason — assistants are far more useful when they can act on Exec Sandbox directly instead of describing what you should do. Single exec tool running caller Python in a network-isolated locked-down sandbox.

What you get

Public OSS MCP server (Go, MIT) exposing a single powerful tool — exec — that runs caller-supplied Python code in a network-isolated, locked-down sandbox and returns stdout / stderr / exit_code. It is the "code-execution mode" building block: instead of flooding an agent's context with hundreds of tool schemas, the agent writes code that orchestrates the work.

What the assistant can call

Once Exec Sandbox is connected, these are the calls the assistant has available:

• MCP_EXEC_TRANSPORT — stdio \
• MCP_EXEC_ADDR — listen address for http/sse
• MCP_EXEC_DEFAULT_TIMEOUT_S — default wall-clock timeout
• MCP_EXEC_MAX_TIMEOUT_S — timeout ceiling
• MCP_EXEC_MAX_OUTPUT_BYTES — combined stdout+stderr cap
• MCP_EXEC_MAX_STDIN_BYTES — stdin size cap
• MCP_EXEC_PYTHON — interpreter path
• MCP_EXEC_AUTH_TOKEN — if set, http/sse require X-MCP-AUTH header (constant-time); empty = off

Configuration and credentials

You will need one environment variable: MCP_EXEC_AUTH_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Exec Sandbox's toolset — MCP_EXEC_TRANSPORT, MCP_EXEC_ADDR, MCP_EXEC_DEFAULT_TIMEOUT_S and 5 more — is a fair guide to whether it matches your workflow. It is maintained by inhuman; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the exec sandbox mcp server does with a few real requests.