HexaHarbor-Agent-Bridge
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
HexaHarbor · 六库仙贼
English · 简体中文 | Setup · Releases · AGPL-3.0-only

Give another coding agent a job without leaving yours. From a Codex chat, for example, you can ask Antigravity to review a change. HexaHarbor hands the task to its native CLI and brings the result back into the same conversation. You keep working in the host you chose; the worker keeps its own tools, login and permissions.
Your first ticket
You need uv, a coordinator such as Codex, and at least one worker CLI already installed and signed in. This example uses Windows PowerShell + Codex + Antigravity:
uv tool install git+https://github.com/WeiBeta/HexaHarbor-Agent-Bridge.git
$bridge = Join-Path (uv tool dir --bin) 'agent-bridge.exe'
codex mcp add agent_bridge -- $bridgeRestart Codex and open a project that has a small change to review. Try asking:
List the available Bridge workers. If Antigravity is available, ask it to review the current Git diff without editing files. Bring back one concrete finding, or say it found none.
First check: list_agents should show Antigravity as available and coordinator.dispatch_enabled should be true. Then use dispatch_ticket with the project directory as cwd. The worker runs there; you can inspect its receipt and check git diff yourself. If the wait expires, keep the returned task_id — continue waiting on that ticket; don't submit a second one.
Not using Codex? Setup by host includes registration examples for Cursor, Kimi Code, ZCode, Grok Build and Claude Code, plus how Devin reads Cursor's configuration.
Related MCP server: opencode-delegate
Which side does what?
Coordinator | The chat where you give instructions and accept the result. Codex, Cursor, Kimi Code, ZCode, Grok Build, Claude Code and Devin can take this role. |
Bridge | A local MCP server. It starts or resumes a worker turn, tracks the task and returns results. No GUI automation or model API proxy. |
Worker | A separate CLI process. Bundled configurations cover Antigravity, Claude Code, Codex CLI, Cursor, DeepSeek Harness, Devin CLI, Grok Build, Kimi Code, MiniMax Code, OpenCode and ZCode. Use |
Local means the bridge runs on your machine, not that prompts never leave it. Each worker uses its own provider and account. The project directory is a working directory, not a sandbox. Results, transcripts and receipts under ~/.agent-bridge are plaintext; keep them outside Git and review them before sharing.
Working with tickets
When you want to… | Use |
Discover workers or remember a routing preference |
|
Send one ticket and collect its receipt |
|
Start several independent tasks or resume an existing session |
|
Check on a quiet worker or read what it did |
|
Stop a turn, inspect sessions or shut down a worker |
|
A wait timeout is not a worker failure. A separate stall_timeout_sec watchdog (default 1800 s) detects a worker that stays silent; check_task reports silent_for_sec. To read long results, follow next_cursor while has_more is true. Bridge doesn't automatically replay a failed prompt. See work tickets and local records, failure diagnostics and quota reporting.
Who decides when to delegate? The default, auto, leaves that to the coordinator. First connect does not ask you to pick a mode. Choose manual for explicit requests only, or eager to prefer delegation on multi-step tasks. Set [coordinator] mode in ~/.agent-bridge/agents.toml or use AGENT_BRIDGE_MODE for one host. The coordinator rulebook is optional; skill auto-install is off by default.
Extend or contribute
Add a worker or connect another coordinator. A standard ACP CLI can often be added through configuration alone.
Development guide: run
uv run --extra dev pytestfrom a clone.tests/is for pytest; live drills uselab/, generated byscripts/setup_lab.pyand not in git.Updates: close coordinators using Bridge, run
agent-bridge upgrade, then restart them. Install this fork from Git; the command isagent-bridgeand the Codex MCP name in the example isagent_bridge.
Derived from Agent-Bridge by FeiZhuLulu. This fork is AGPL-3.0-only; the upstream MIT notice is preserved. See NOTICE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted coding agent: start, follow up on and stop tasks that can open GitHub pull requests.
Command center for developers coordinating AI coding agents across projects.
Dispatch work to Kadmo's AI agents, read tasks and runs, edit skill packs, playbooks and routing
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables supervising and coordinating local coding agents across allowed repositories, including inspecting context, reviewing sessions, launching or continuing tasks, and retrieving redacted logs under owner-controlled access.1-
- AlicenseNot gradedqualityBmaintenanceEnables agents to discover and configure model routing, delegate coding tasks with context files, scope restrictions, and verification, and resume existing sessions with delta instructions or review feedback.MIT
- AlicenseNot gradedqualityBmaintenanceProvides a shared task state for local coding agents, letting them bootstrap a project, list and create tasks, resume work, write checkpoints, inspect configured routes, and plan worker runs. It also exposes a bounded delegation call that invokes configured local agent clients, returning a proposal that requires human review since it may consume quota or balance.PolyForm Noncommercial 1.0.0
- AlicenseBqualityCmaintenanceEnables AI agents to start, monitor, follow up on, stop, and collect results from headless Claude Code CLI sessions, with queuing, budgets, locks, and wake-up notifications.9MIT