Skip to main content
Glama
francisco-perez-sorrosal

wasmer-sandbox-mcp

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort for the Edge server. Falls back to FASTMCP_PORT, then 8000.8000
DB_HOSTYesThe database host for the Edge Postgres connection.
DB_PORTYesThe database port for the Edge Postgres connection.
DB_USERYesThe database user for the Edge Postgres connection.
DB_DATABASEYesThe database name for the Edge Postgres connection.
DB_PASSWORDYesThe database password for the Edge Postgres connection.
FASTMCP_PORTNoFallback port if PORT is not set.8000

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
run_pythonA

Run Python code inside an isolated Wasmer sandbox and get back its output.

Use it to execute code you do not want touching this machine: untrusted snippets, experiments, quick calculations, anything with side effects you would rather contain. code is passed to python -c, so print what you want to see. Set network=true only when the code must reach the internet — that routes to a second sandbox with the host's network and its own separate state. Returns exit_code, stdout, stderr, reason and duration_ms; a non-zero exit_code is a normal result, not an error.

The sandbox is long-lived: files written and packages installed by earlier calls are still there, and anything this code writes stays for the next one. Call reset_sandbox when you want a clean slate.

run_commandA

Run any command available inside the Wasmer sandbox, with arguments.

Use it for non-Python work in the sandbox — a shell utility, or a binary that install_sandbox_package added. command is the command name, and args its arguments as a list (not a shell string: there is no shell splitting, quoting or piping). Returns the same result shape as run_python.

The sandbox is long-lived, so this command sees files and packages left by earlier calls, and its own side effects persist until reset_sandbox.

write_sandbox_fileA

Write a text file inside the sandbox, creating parent directories as needed.

Use it to put a script, a fixture or input data where sandboxed code can read it — run_python and run_command in the same sandbox see the same filesystem. Use an absolute path such as /tmp/input.json. The network flag selects which sandbox, and the two do not share a filesystem: write and read with the same value. Overwrites an existing file without asking. Returns the path and the number of bytes written.

read_sandbox_fileA

Read a text file from inside the sandbox.

Use it to collect a file that sandboxed code produced, or to check what an earlier write_sandbox_file left behind. Long files come back capped as head + tail with the elision marked, and truncated: true says so. network selects which sandbox, and a file written to one is not visible in the other.

list_sandbox_dirA

List the contents of a directory inside the sandbox.

Use it to find out what is actually there before reading or running something — especially after install_sandbox_package, or when a read_sandbox_file came back not_found. Returns each entry's name, kind and size.

install_sandbox_packageA

Install a Wasmer registry package into the sandbox and report the commands it adds.

Use it to get a tool the sandbox does not already have — the guest starts with only Python. package is a registry name like wasmer/edgejs or wasmer/edgejs@0.2.0. The returned commands are exactly the names run_command can then call. The install persists for the life of the sandbox, so it survives later calls until reset_sandbox.

get_sandbox_infoA

Report whether the sandboxes are warm, and what they are running.

Use it when a call came back warming, when one was unexpectedly slow, or before a long task. There are two sandboxes, one per network policy (off and host), warmed independently; warm: false means the first call for that policy pays the ~26 s download-and-compile cost.

reset_sandboxA

Throw away the sandbox's accumulated state and start a fresh one.

Use it when earlier files, installed packages or environment changes are getting in the way, or when a sandbox is behaving oddly. Pass network as "off" or "host" to reset just that one; omit it to reset both. The replacement warms in the background, so the next call may answer warming — that is expected.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/francisco-perez-sorrosal/wasmer-sandbox-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server