Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DOCKER_CPUSNoCPUs per container2
DOCKER_IMAGENoBase imagetaw-computer-base
SANDBOX_TYPENoauto / docker / firecrackerauto
MAX_SANDBOXESNoMax concurrent VMs3
DOCKER_MEMORY_MBNoRAM per container4096
DESKTOP_RESOLUTIONNoScreen resolution1280x720

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
vm_createA

Create a new sandbox (isolated Ubuntu mini-computer with shell, Chrome + CDP, VNC, xfce4). IMPORTANT: Before creating, check if the user has saved snapshots by looking at the available_snapshots field in the response. If snapshots exist, ask the user whether they want to resume from a snapshot or start fresh. Set use_snapshot: true to resume. Backend is auto-detected: Firecracker microVM if KVM available, Docker otherwise. Returns the sandbox id used by all other tools, plus a noVNC URL the human can open to watch what the AI is doing. IMPORTANT: Always present vnc_url exactly as returned — never modify the URL path, filename, or query parameters.

vm_listA

List active sandboxes created in this MCP session.

vm_destroyA

Destroy a sandbox and free its ports. By default the VM filesystem is saved as a snapshot so recreating with the same label resumes where you left off. Set save_snapshot to false to destroy without saving (e.g. when the VM contains sensitive data the user does not want persisted). Use vm_reset to also delete any previously saved snapshot.

vm_resetA

Reset a VM to a clean state. Destroys the current VM AND deletes its saved snapshot, so the next vm_create with the same label starts fresh from the base image.

vm_restartA

Restart a sandbox. Stops and starts the container — all files, databases, and installed packages are preserved. Only processes are restarted.

vm_statusA

Get resource usage (CPU, memory, disk, uptime, top processes) and port mappings for a sandbox. Use to diagnose OOM, high CPU, or check available disk space.

vm_renameA

Rename a running VM by changing its label. The label is used for snapshot naming — renaming does NOT migrate existing snapshots (they stay under the old label).

snapshot_listA

List all saved snapshots. Each snapshot can be resumed by calling vm_create with the same label and use_snapshot=true.

snapshot_deleteA

Delete a saved snapshot by label. This frees disk space and means the next vm_create with this label will start fresh.

execA

Run a shell command inside the sandbox. Returns combined stdout+stderr. Use for any CLI work: git, npm, pip, apt, curl, etc.

fs_writeB

Write content to a file inside the sandbox (creates parent dirs as needed).

fs_readC

Read a file inside the sandbox.

fs_editA

Replace a string in a file. Fails if old_string is not found. Set replace_all=true to replace every occurrence.

fs_listA

List files in a directory (ls -la, or recursive find with depth 3).

fs_searchB

grep -rn for a pattern in a directory.

code_searchA

Search codebase content using ripgrep. Much faster and smarter than fs_search — supports regex, file type filters, context lines, and higher result limits.

desktop_screenshotA

Take a JPEG screenshot of the sandbox desktop (xfce4) and return as image content.

desktop_clickC

Click at (x,y) on the sandbox desktop. button=1 left, 2 middle, 3 right.

desktop_typeC

Type text into the focused window via xdotool.

desktop_keyC

Press a key combo via xdotool, e.g. "Return", "ctrl+l", "alt+Tab".

desktop_scrollD

Scroll at (x,y).

desktop_dragB

Drag from (from_x, from_y) to (to_x, to_y) on the sandbox desktop.

browser_openB

Open Chrome inside the sandbox (or navigate the existing tab) at the given URL, then return a JPEG screenshot.

browser_closeC

Kill all Chrome processes inside the sandbox.

browser_navigateB

Navigate the sandbox Chrome to a URL via CDP (Playwright). Returns final URL and page title.

browser_snapshotA

Inject numbered overlays on every visible interactive element (Set-of-Mark prompting), screenshot the page, return both the screenshot and element refs. Use browser_click_ref / browser_type_ref to interact.

browser_click_refC

Click an element by its ref number from the most recent browser_snapshot.

browser_type_refB

Focus an element by ref and type text into it. Set submit=true to press Enter after.

browser_extractA

Read text content from the page. With selector: returns innerText of matching elements. Without: full page text.

browser_evalC

Run a JavaScript expression in the page context and return the result.

browser_wait_forB

Wait until a condition holds (selector visible, text appears, or network idle).

browser_console_logsC

Return captured browser console logs (errors, warnings, info) from the current page.

browser_network_errorsC

Return captured network request failures (404s, CORS errors, etc.).

browser_run_testB

Run a Playwright test script against the browser inside a VM. Has page, browser, context, and chromium available.

web_searchC

Search Google and return up to 8 organic results as {title, url, snippet}.

file_uploadB

Upload a file into a VM. Pass content as base64 string (max 50MB).

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/tawgroup/taw-computer'

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