gemini-relay
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGY_CLI_PATH | No | Custom path to the `agy` binary (`agy.exe` on Windows, `/usr/local/bin/agy` on Unix). | auto-detected |
| GEMINI_CLI_PATH | No | Custom path to legacy `gemini` CLI executable. | auto-detected |
| AGY_PRINT_TIMEOUT | No | Timeout forwarded to `agy --print-timeout`. | 44m |
| GEMINI_MCP_BACKEND | No | Active engine backend: `agy` (Antigravity CLI, recommended) or `gemini` (legacy). | agy |
| GEMINI_MCP_TIMEOUT | No | Process execution timeout in minutes. | 45 |
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 | {} |
| logging | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gemini-askA | Send one prompt to Google Gemini (or the Claude and GPT-OSS models the Antigravity CLI also offers) and get the answer back: questions, code review, analysis, edits, structured JSON. Reference project files with @path to send their contents along. Pass conversationId to continue a thread. For a phased implementation blueprint use gemini-plan; for idea generation use gemini-brainstorm; for everything else use this. |
| gemini-planA | Produce a read-only, phased implementation blueprint for one task — steps, dependencies, risks — on Gemini's highest reasoning effort. Never edits files and never answers general questions; use gemini-ask for those. |
| gemini-imageA | Generate images from text descriptions through the Antigravity CLI's image generation tool. Supports aspect ratio and output size selection, plus optional export directly into your project. |
| gemini-modelsA | Lists available Gemini models, default selections, reasoning capabilities, and active backend status. |
| gemini-doctorA | Diagnose and verify Gemini CLI / Antigravity CLI (agy) installation, active backend, CLI version, and system readiness. |
| gemini-brainstormA | Generate a ranked list of ideas for an open-ended challenge using a named creativity method (SCAMPER, design thinking, lateral, divergent, convergent), with optional feasibility analysis. Ideation only: use gemini-ask for answers and gemini-plan for implementation blueprints. |
| gemini-fetch-chunkA | Retrieve one chunk of a chunked changeMode reply from gemini-ask, by the cacheKey and chunkIndex that reply reported. No model turn; the cache lives 10 minutes. |
| gemini-conversationsA | List recent Gemini conversations the relay can resume: id, last activity, working directory, first prompt. Pass an id to gemini-ask as conversationId to continue that thread. Reads agy's local store; no model turn. |
| gemini-cancelA | Stop every Gemini CLI run the relay has in flight right now: a slow gemini-ask, gemini-plan, gemini-brainstorm or gemini-image. Each cancelled call returns an error to its caller. Nothing else is touched. |
| gemini-pingA | Liveness check: echoes the prompt back from the relay itself, without touching the CLI or any model. Use gemini-doctor to check the CLI. |
| gemini-helpA | Print the active backend CLI's own --help text (agy or gemini), to see which flags the installed version supports. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| gemini-ask | Ask Gemini a question or hand it a review, with optional model, reasoning effort, read-only mode, and structured output. |
| gemini-plan | Create a detailed implementation blueprint for a task using Gemini's high-effort reasoning and plan mode. |
| gemini-image | Generate an image from a prompt with optional aspect ratio and local file output. |
| gemini-models | List available Gemini models and active CLI backend capabilities. |
| gemini-doctor | Run diagnostic checks on Gemini CLI / Antigravity CLI environment and report status. |
| gemini-brainstorm | Brainstorm ideas for a challenge with a chosen creativity method and feasibility analysis. |
| gemini-fetch-chunk | Fetch the next chunk of a response |
| gemini-conversations | List recent Gemini conversations and their ids. |
| gemini-cancel | Cancel the Gemini runs currently in flight. |
| gemini-ping | Echo a message back to prove the relay is alive. |
| gemini-help | Show the backend CLI's --help output. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool targets a distinct mode: gemini-ask for general answers, gemini-plan for blueprints, gemini-brainstorm for ideation, and gemini-image for generation. The descriptions explicitly cross-reference which tool to use, so there is little risk of selecting the wrong one.
All tools share the gemini- prefix and kebab-case style, making the family instantly recognizable. However, gemini-models and gemini-conversations are noun-style subcommands while others like gemini-ask and gemini-fetch-chunk are verb-style, a minor deviation from a strict verb_noun pattern.
11 tools is well within the ideal range and each tool earns its place: four generation modes, conversation and chunk retrieval support, cancellation, and diagnostics. There is no obvious redundancy or padding.
The surface covers generation, planning, ideation, images, conversation resumption, chunked-response retrieval, cancellation, and environment diagnostics—no dead ends for the relay's stated purpose. Optional capabilities like conversation deletion are not implied by the server's scope.