Skip to main content
Glama
vovayartsev-dice

devcontainer-mcp

bash

Run shell commands inside a devcontainer, returning output and exit codes. Use for builds, tests, and package management.

Instructions

Run a shell command inside the project's devcontainer and return its combined stdout/stderr and exit status.

Mirrors Claude Code's built-in Bash tool, but every command executes inside the devcontainer (via devcontainer exec ... bash -lc) rather than on the host. Use it for builds, tests, package installs and any other shell work that should happen in the container environment.

The command string is interpreted by bash inside the container, so pipes, &&, ||, globs, redirects, env expansion and quoting all behave as in a normal shell.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesThe shell command line to execute. It is run with `bash -lc` inside the devcontainer, so pipes, &&, globs, redirects and environment expansion all work.
cwdNoWorking directory inside the container to run the command from. Defaults to the workspace root.
envNoExtra environment variables to forward into the container, either as an object map {"KEY": "VALUE"} or a list of "KEY=VALUE" strings. Forwarded via repeated --remote-env.
timeoutNoTimeout in milliseconds. Defaults to 120000, capped at 600000. On timeout the process group is killed and the result is flagged as an error.
descriptionNoOptional human-readable description of what the command does. Logged for observability; not required.
workspaceFolderNoHost path to the workspace/worktree that holds the .devcontainer config. Defaults to the server's working directory, or $DEVCONTAINER_WORKSPACE_FOLDER when set.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes execution via devcontainer exec with bash -lc, shell behavior (pipes, globs, redirects), and timeout handling (process group killed, flagged as error). No annotations exist, so description carries full burden; it covers major behavioral traits but omits side effects or state persistence.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise paragraphs with front-loaded purpose. Every sentence adds value; no redundancy. Efficiently communicates core function and key details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, no output schema, and no siblings, the description covers purpose, usage, execution model, timeout, and return value (combined stdout/stderr and exit status). Parameter details are fully handled by schema. Complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description adds little beyond reinforcing shell behavior for the command parameter. Baseline 3 is appropriate as description does not introduce new parameter-specific meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs shell commands inside the devcontainer, returns combined stdout/stderr and exit status, and specifies use cases like builds and tests. It distinguishes itself from host execution by emphasizing container context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use it for builds, tests, package installs and any other shell work that should happen in the container environment.' Provides clear usage context, though no explicit when-not or alternative tools are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/vovayartsev-dice/devcontainer-mcp'

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