agent-shuttle-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BRIDGE_CODEX_URL | No | URL for Codex agent delegation. | |
| BRIDGE_AGENTS_JSON | No | Routes requests to any agent mapped in this environment variable. | |
| BRIDGE_ANTIGRAVITY_URL | No | URL for Antigravity agent delegation. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_agentA | Delegate research, code review, implementation or a second opinion to a local AI agent: Antigravity (antigravity), Codex (codex), OpenCode (opencode), Claude Code (claude_code), or an agent_id from list_agents. Делегирование: исследование, ревью, реализация, второе мнение. Use for an actual request to have another agent perform work. Answer general explanations and advice directly; mentioning an agent or a second opinion alone does not request delegation. Shuttle manages local servers automatically. Inspect get_agent_info before selecting an enforceable tool policy; research including web access depends on that agent's capabilities. For Antigravity web research choose web_research when advertised; read_only allows local files only. Preserve the user's explicit agent and model. Use submit_task for long work. |
| get_agent_infoA | Inspect live models, account quota and enforceable tool policies for Antigravity, Codex, Claude Code, OpenCode or a configured ACP agent before delegating research, review, implementation or a second opinion. Manages the local server automatically. This checks live metadata without a model turn; use list_agents for offline inventory. |
| ask_antigravityC | Delegate to Antigravity. Default: read_only; choose workspace_write for file edits. Scoped policies enforce native file tools and block shell/MCP/subagents. Servers and per-conversation permission hooks are managed automatically. |
| ask_codexC | Delegate to Codex, launching its A2A server when absent. Omit model unless requested. |
| submit_taskA | Delegate research, code review, implementation or a second opinion to a local AI agent: Antigravity (antigravity), Codex (codex), OpenCode (opencode), Claude Code (claude_code), or an agent_id from list_agents. Делегирование: исследование, ревью, реализация, второе мнение. Use for an actual request to have another agent perform work. Answer general explanations and advice directly; mentioning an agent or a second opinion alone does not request delegation. Shuttle manages local servers automatically. Inspect get_agent_info before selecting an enforceable tool policy; research including web access depends on that agent's capabilities. For Antigravity web research choose web_research when advertised; read_only allows local files only. Preserve the user's explicit agent and model. Use submit_task for long work. Returns a task ticket immediately; use check_task/wait_task, then get_result. Reuse request_id when retrying submission. |
| get_task_changesB | Describe an isolated task's saved changes; no files are modified. |
| get_task_diffC | Read a bounded page of an isolated task's Git binary patch. |
| apply_task_changesB | Explicitly apply reviewed changes if touched source files still match the base. |
| discard_task_changesC | Explicitly delete an isolated task's saved change and owned worktree. |
| check_taskC | Read the current task snapshot without waiting for the worker. |
| wait_taskC | Wait within a separate budget; expiry returns a snapshot and never cancels work. |
| cancel_taskB | Stop the delegated task and wait for backend cleanup; repeated cancellation is safe. |
| get_resultC | Read a bounded result page; follow next_cursor until it is null. |
| get_transcriptB | Read a page of A2A task history and artifacts; status updates may be absent. |
| get_eventsB | Read Shuttle's ordered event journal. Save total_size to poll after the current end. |
| get_event_pageC | Read full JSON data for a journal event with data_truncated=true. |
| list_agentsA | Discover local Antigravity, Codex, Claude Code, OpenCode and configured ACP agents for delegation, research, code review, implementation and second opinions. Lists agent_id, command availability and configuration errors without starting agent processes, contacting models or verifying authentication. Use get_agent_info for live readiness, models and tool policies. Поиск агентов для делегирования задач. Use when asked to discover actual available local agents or while preparing authorized delegation. General explanations and advice about agents or second opinions do not require an inventory of the user's installed agents. |
| get_antigravity_infoB | Read Antigravity's current models, effort options and account quota without an agent turn. |
| get_codex_infoA | Read Codex's current models, supported efforts and account quota without an agent turn. |
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 19 tools
Four tools perform delegation with near-identical purposes: ask_agent, submit_task (whose description is literally identical plus one sentence), ask_antigravity, and ask_codex. Likewise get_agent_info, get_codex_info, and get_antigravity_info overlap, leaving the agent to guess whether to use the generic or per-backend variant. The read-side tools (get_result, get_transcript, get_events, get_event_page) are distinguishable only by careful reading.
Almost everything follows a verb_noun snake_case pattern (get_result, submit_task, check_task, wait_task, cancel_task, list_agents, get_task_diff). Minor deviations exist: ask_antigravity/ask_codex drop the '_agent' suffix used by ask_agent, and apply_task_changes/discard_task_changes use a three-part noun phrase.
At 19 tools the surface is heavy and includes clear redundancy: ask_antigravity/ask_codex duplicate ask_agent, and get_codex_info/get_antigravity_info duplicate get_agent_info. The task lifecycle (submit/check/wait/cancel/diff/apply/discard) legitimately needs several tools, but a leaner set would be easier to navigate.
The domain is well covered end-to-end: discovery (list_agents), capability inspection, sync and async delegation, polling, waiting, cancellation, paginated results, transcripts, event journal, and diff review/apply/discard. Gaps are minor, e.g. no explicit follow-up message or task listing/cleanup operation.