Skip to main content
Glama

agy

Destructive

Run a prompt through a CLI agent that executes coding tasks, supports multi-turn conversations, extra workspace directories, and sandbox security. Returns responses non-interactively.

Instructions

Run a prompt through the Antigravity CLI (agy) in non-interactive print mode and return the response. Supports multi-turn continuation, extra workspace directories, sandbox, and auto-approval of tool permissions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesThe coding task, question, or analysis request
sessionIdNoOptional session ID for multi-turn context. The first turn starts a fresh agy conversation; later turns in the same session continue it via `agy --continue`. Note: agy continues the most-recent conversation globally, so avoid interleaving sessions or manual agy usage mid-session.
resetSessionNoReset the session history before processing this request (starts a fresh agy conversation)
conversationIdNoResume a specific agy conversation by ID (e.g. one obtained from the Antigravity app). Maps to `agy --conversation <id>` and takes precedence over session continuation.
continueConversationNoForce `agy --continue` to continue the most recent conversation, regardless of session state
addDirsNoExtra directories to add to the agy workspace (maps to repeated `--add-dir` flags)
sandboxNoRun agy in a sandbox with terminal restrictions enabled (`--sandbox`)
skipPermissionsNoDANGEROUS: auto-approve all tool permission requests without prompting (`--dangerously-skip-permissions`). Required for agy to use tools non-interactively, but lets it modify files/run commands unattended.
printTimeoutNoTimeout for print mode as a Go-style duration (e.g. "90s", "5m", "1h30m"). Maps to `--print-timeout`. Defaults to 5m.
Behavior4/5

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

Annotations indicate destructiveHint=true and openWorldHint=true. The description adds significant behavioral context: non-interactive mode, multi-turn continuation, sandbox, and auto-approval with danger warnings. It also warns about session interleaving, going beyond what annotations provide.

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?

The description is a single, well-structured sentence that encapsulates all key features without redundancy. Every clause adds value, and the main action is front-loaded.

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

Completeness4/5

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

Given 9 parameters and no output schema, the description covers the core functionality (print mode, multi-turn, sandbox, auto-approval). It does not explain the return format explicitly, but 'return the response' implies CLI output. Error handling is not addressed.

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 baseline is 3. The description does not add new parameter-level details beyond the schema's own descriptions, which are already thorough (e.g., sessionId warning, skipPermissions danger). Hence the description adds marginal value.

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 action ('Run a prompt through the Antigravity CLI'), the resource (agy), and the mode (non-interactive print mode). It distinguishes the tool from siblings like changelog, help, listSessions, and ping, which serve different purposes.

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

Usage Guidelines3/5

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

The description provides clear context for the tool's functionality but does not explicitly state when to use it versus alternatives. The sibling tools are different, but no direct usage guidance or exclusions 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/toonPt0473/agy-mcp-server'

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