antigravity-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGY_PATH | No | Path to the agy executable file. | agy |
| AGY_PROXY | No | Proxy setting. off forces direct connection; http://host:port specifies a proxy; default auto detects automatically. | auto |
| AGY_SANDBOX | No | Pass --sandbox to agy. Recommended to enable. | false |
| AGY_TIMEOUT | No | Global timeout in seconds. AGY_TIMEOUT_<TOOL> can be used to set a timeout for an individual tool. | 1200 |
| AGY_ON_FAILURE | No | Failure handling mode. strict means fail with an error and prevent the main model from taking over automatically. | fallback |
| AGY_TASK_TTL_MS | No | Retention duration in milliseconds for completed tasks. | 3600000 |
| AGY_ALLOWED_ROOTS | No | Directories allowed to be accessed; multiple values separated by the path separator. | process cwd |
| AGY_DEFAULT_MODEL | No | Fixed default model. If a tier is missing, it automatically upgrades to High. | |
| AGY_QUOTA_FAILOVER | No | Automatically switch models when quota is exhausted. Disabled by default because it may replay tasks and cause duplicate side effects. | false |
| AGY_TIMEOUT_<TOOL> | No | Timeout in seconds for a specific tool, where <TOOL> is the tool name. | |
| AGY_MAX_OUTPUT_CHARS | No | Maximum number of output characters before truncation. | 50000 |
| AGY_SKIP_PERMISSIONS | No | Pass --dangerously-skip-permissions to agy. Not recommended. | false |
| AGY_MODEL_LIST_TIMEOUT_MS | No | Timeout in milliseconds for fetching the model list. | 120000 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_filesA | Delegate file analysis to the Antigravity CLI (Gemini) instead of reading files yourself. USE THIS whenever a file is large (>200 lines) or the task spans more than 3 files: logs, database dumps, generated code, cross-file reviews, comparisons. The files never enter your context — only the answer does. |
| deep_searchA | Delegate codebase archaeology to the Antigravity CLI: git log/diff/blame spelunking, wide greps across a repo, 'when/why did X change', 'where is Y used'. USE THIS instead of running many search commands yourself — it saves your context. |
| web_lookupA | Delegate a web/documentation lookup to the Antigravity CLI (Gemini with web access): library docs, API references, error messages, current versions, external knowledge. USE THIS when you need information you don't have or that may be newer than your training data. |
| adversarial_reviewA | Get an adversarial second opinion from a different model family (Gemini Pro). ALWAYS use this for plan critiques, design reviews, and pre-merge code review: it hunts for flaws, edge cases, security issues, and unstated assumptions you may have missed. |
| follow_upA | Continue a previous Antigravity session by session_id (returned by every other tool). USE THIS for follow-up questions about a prior delegation — the full prior context is already on agy's side, so you don't resend anything. |
| delegateB | Raw delegation to the Antigravity CLI for heavy tasks that don't fit the other tools. agy has full tool access (shell, file reads, web) in the given cwd. |
| list_modelsC | List the live model directory returned by the authenticated Antigravity CLI. |
| start_taskC | Start a long-running task. Use task_status to poll and cancel_task to stop it. |
| task_statusC | Read task state and final result. |
| cancel_taskC | Cancel a running Antigravity task. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
The four domain-specific delegations (analyze_files, deep_search, web_lookup, adversarial_review) are well differentiated by target domain, but the raw `delegate` tool explicitly claims 'heavy tasks that don't fit the other tools,' which is a superset of all four and invites misselection. Similarly, `start_task` vs `delegate` and `follow_up` vs `delegate` have blurry boundaries (sync vs async vs continuation) that descriptions only partially resolve.
The task lifecycle group (start_task, task_status, cancel_task) is a clean verb_noun pattern, and analyze_files/deep_search/web_lookup follow suit. However, the set mixes in bare verbs and non-verb forms — `delegate`, `follow_up`, `list_models`, and the adjective-noun `adversarial_review` — so no single predictable convention runs through the whole surface.
Ten tools is well within a comfortable range for a delegation bridge, and each maps to a recognizable capability (domain delegation, raw delegation, session continuation, task lifecycle, model listing). The only redundancy is the catch-all `delegate` sitting alongside four specialized delegators, which is slightly more surface than strictly needed.
The async task lifecycle is covered end to end (start_task, task_status, cancel_task) and follow_up closes the multi-turn session loop, so there are no dead ends in the core delegation flow. Minor gaps remain: no way to enumerate active tasks or list prior sessions/session_ids, forcing the agent to track IDs manually.