Agent Rack
未申請MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client — background sessions, terminal dashboard, structured code review
インストール
npx agent-rack setup未申請リスティング
このMCPサーバーはあなたのものですか？
このリスティングは公開情報から自動的にインデックスされました。申請することで、ページの編集、互換性の設定、成長ツールのアンロックができます。2分以内に完了します。
このサーバーを申請するツール（40個）
adversarial
boolean
agent
string
agent_list_available
No parameters. Lists every configured agent and whether its binary is on $PATH.
agent_run
agent_session_cancel
agent_session_create
Same execution parameters as agentrun (agent, prompt required; workspace, mode,
agent_session_delete
agent_session_logs
agent_session_send
agent_session_status
agent-rack-review-handling
An agentreview call returns
agent-rack-tool-selection
Delegating any task to a sub-agent through agent-rack
agents
Map of agent id → { name, command, args, transport, env, description, model, inheritEnv }
allowedWorkspaces
Absolute directory paths agents may be launched in. Every tool call resolves symlinks and validates against this list before any subprocess spawns. See the caveat under Security model — this constrains the working directory, not everything the process can reach.
background
boolean
baseRef
string
cursor
number
enableSseSidecar
When transport is stdio (the default), also open a loopback SSE listener on the same session state, so agent-rack session status/tail and the dashboard can observe sessions created over the stdio connection with no separate server. Default true; same bearer-token protection as security.requireSseAut
focus
string
followUpMode
Agents
limit
number
line_start
/lineend may be 0 for whole-file, deleted-file, or architectural findings.
live
opencode
message
string
mode
string
model
string
OpenCode
agent-rack install --target opencode
port
HTTP port when transport is sse, or for the sidecar below (default 8987)
prompt
string
resume
claude, codex
scope
working-tree \
security.executionPolicy
read-only \
security.maxConcurrentSessions
Cap on simultaneously running background sessions (default 5)
security.requireSseAuth
Require a bearer token on the SSE transport (default true). See SSE authentication.
security.sanitizeEnv
Strip env vars matching credential patterns before spawning agents (default true). Prefer per-agent inheritEnv.
sessionId
string
tail
number
timeoutSeconds
number
transport
stdio (default, for per-client local IDE integration) or sse (localhost HTTP-SSE, for a shared server and dashboard)
workspace
string