Skip to main content
Glama
josephjerryrhule

agy-mcp

by josephjerryrhule
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

agy_execute

Delegates heavy coding, editing, and testing tasks to an autonomous headless agent, showing live progress and preserving context window.

Instructions

Spins up a headless Antigravity (agy) agent to autonomously execute heavy coding, editing, refactoring, research, or testing tasks with live streaming progress, thinking token logs, tool tracing, and token savings metrics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoExecution mode: accept-edits (standard autonomous editing) or plan (planning mode).accept-edits
asyncNoRun task asynchronously in background. RECOMMENDED in Claude Desktop for any real coding tasks (>45s) to prevent Claude Desktop 60-second MCP client timeouts. Check status with agy_check_task.
modelNoOptional specific model identifier for agy.
effortNoReasoning effort (low, medium, high). Default is high.high
instructionsYesDetailed step-by-step instructions for agy. Specify target file paths, constraints, test commands, and exact functional requirements.
workspace_dirNoTarget workspace directory path (MANDATORY in Claude Desktop to point to the project repo, otherwise agy runs inside Claude desktop internal directory). Defaults to current working directory.
timeout_secondsNoMax execution time in seconds (default 600 = 10 minutes).
include_git_diffNoInclude git status and diff statistics of files modified during execution.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • addedInput schema / properties / async
      Added value: +{
+  "default": false,
+  "description": "Run task asynchronously in background. RECOMMENDED in Claude Desktop for any real coding tasks (>45s) to prevent Claude Desktop 60-second MCP client timeouts. Check status with agy_check_task.",
+  "type": "boolean"
+}
    • changedInput schema / properties / workspace_dir / description
      Previous value: -"Target workspace directory path (absolute path recommended, especially in Claude Desktop). Defaults to current working directory."New value: +"Target workspace directory path (MANDATORY in Claude Desktop to point to the project repo, otherwise agy runs inside Claude desktop internal directory). Defaults to current working directory."
  2. Changed1 schema field changedv1.2.1
    • changedInput schema / properties / workspace_dir / description
      Previous value: -"Target workspace directory path. Defaults to current working directory."New value: +"Target workspace directory path (absolute path recommended, especially in Claude Desktop). Defaults to current working directory."
  3. First observedv1.2.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description must carry safety/behavior details; it does disclose headless autonomous execution and live streaming/metrics, which is meaningful. However, it does not mention side effects or that the agent will directly modify files, or what happens on timeout/failure—behavioral gaps given no annotation coverage.

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

Conciseness4/5

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

A single dense, front-loaded sentence that places the core action first and then lists monitoring features. It is not bloated, though the feature list could be trimmed without losing invocation-relevant content.

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

Completeness3/5

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

Given no output schema and no annotations, the definition is serviceable but incomplete: an agent is not told what agy_execute returns (e.g., task ID, initial stream) or how to monitor/continue after an async invocation. Sibling tool names imply that workflow but the description does not state it.

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 3 is appropriate. The description itself adds no parameter-specific semantics; the async, mode, and workspace_dir behavior is already fully explained in the schema.

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

Purpose4/5

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

The description clearly identifies a specific action ('spins up a headless Antigravity agent') and scope ('execute heavy coding, editing, refactoring, research, or testing tasks'), which differentiates it from status/check/continue siblings. It does not explicitly compare itself to codex_execute or say when to prefer agy_continue, so it stops short of full differentiation.

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?

The phrase 'heavy ... tasks' plus the async parameter's recommendation for 'real coding tasks (>45s)' and pointer to agy_check_task give clear context on when to use this tool. It does not state exclusions or direct users to codex_execute for alternative scenarios.

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

Deploy Server

Other Tools