orchestrator-mcp

orchestrator-mcp

Multi-model agent orchestration MCP server that enables plan-code-review-deliver pipelines with configurable providers and models.

Category
Visit Server

README

orchestrator-mcp

多模型 Agent 编排 MCPplan → code → review → deliver

  • Handoff schema 固定schemas/
  • Provider 按厂商(deepseek / moonshot / zhipu / openai),model 按 stage 配置
  • 别名glm → zhipu,gpt → openai
  • 凭证:环境变量 → WebUI 本地 JSON → ~/Desktop/服务器.md
  • Web 配置界面:编辑 Provider Key / Base URL / 默认模型,以及各 Profile 的 Stage 模型

快速开始

cd orchestrator-mcp
./verify.sh              # 离线 stub 自测(含 WebUI API 冒烟)
./start.sh               # MCP :18067
./start-webui.sh         # 配置 WebUI :18068 → http://127.0.0.1:18068

# 可选:只测 plan 阶段真实 DeepSeek 调用
ORCHESTRATOR_LIVE_TEST=1 ./verify.sh

Web 配置界面

功能 说明
Providers 编辑 api_keybase_urldefault_model;写入 data/providers.local.json
Stages 按 Profile 覆盖 plan/code/review/deliver 的 provider + model;写入 data/stages.local.json

本地配置文件不进 git。环境变量仍优先于 WebUI 写入的值。

Profile

Profile 用途
daily-dev-stub 离线自测,不调 API
daily-dev deepseek plan / glm code / gpt review / moonshot deliver
example-kimi-plan 示例:plan 换 kimi

同一 OpenAI 账号下 plan 用 gpt-4o-mini、code 用 gpt-5:只改 YAML 里各 stage 的 model不用建两个 provider。

stages:
  plan:
    provider: gpt
    model: gpt-4o-mini
  code:
    provider: gpt
    model: gpt-5

凭证环境变量

Provider Env 默认 Base URL
deepseek DEEPSEEK_API_KEY https://api.deepseek.com/v1
moonshot MOONSHOT_API_KEY https://api.moonshot.cn/v1
zhipu/glm ZHIPU_API_KEY https://open.bigmodel.cn/api/paas/v4
openai/gpt OPENAI_API_KEY https://api.openai.com/v1 · wire_api=chat
codex-lb/codex CODEX_LB_API_KEY https://codex-lb.vvicat.dev/backend-api/codex · wire_api=responses

Codex 中转(Responses API)

与 Codex CLI 配置对应关系:

model = "gpt-5.4"
model_reasoning_effort = "medium"
model_provider = "codex-lb"
env_key = "CODEX_LB_API_KEY"

[model_providers.codex-lb]
base_url = "https://codex-lb.vvicat.dev/backend-api/codex"
wire_api = "responses"

在 WebUI Providers → Codex 中转 填写:

字段
API 密钥 CODEX_LB_API_KEY
Base URL https://codex-lb.vvicat.dev/backend-api/codex(不要写成 /code
默认模型 gpt-5.4
Wire API responses
Reasoning Effort medium

Stage 里把 review/deliver 的 provider 选 codex-lb(或别名 codex),model 填 gpt-5.4

注意/chat/completions 在该中转上返回 405;必须用 Responses 协议。

可选覆盖:CODEX_LB_BASE_URLDEEPSEEK_BASE_URLMOONSHOT_BASE_URLZHIPU_BASE_URLOPENAI_BASE_URL

服务器.md 标签(下一行或同行):deepseekApiKeymoonshotApiKeyzhipuApiKeyopenaiApiKey

Workspace 项目上下文(与 IDE 共用源文件)

MCP 不单独维护记忆文件。传入 workspace(或设置 ORCHESTRATOR_WORKSPACE)后,每个 stage 直接从磁盘读取与 Cursor/Codex 相同的源文件并注入 prompt:

路径 说明
AGENTS.md / CLAUDE.md / agent.md 项目级 agent 说明
.cursor/rules/* Cursor 规则
.learnings/*.md self-improving 沉淀
profile skills: 加载对应 SKILL.md 全文
git branch、dirty files、diff --stat
  • orchestrate_run_start / orchestrate_run_pipelineworkspaceextra_context(仅本次 run)
  • orchestrate_workspace_context:预览将读取哪些文件

MCP 工具

工具 说明
orchestrate_list_providers 各 provider 是否已配置 key
orchestrate_provider_check 检查单个 provider
orchestrate_workspace_context 预览 workspace 项目上下文
orchestrate_run_start / orchestrate_dispatch / orchestrate_run_pipeline 编排执行(支持 workspace
orchestrate_stage_override 运行时换 provider/model

Cursor 配置

本仓库已在 .cursor/mcp.json 写好配置(stdio 模式,不用手动 ./start.sh)。

  1. 用 Cursor 打开 localopenclaw 仓库根目录
  2. Settings → Tools & MCP,确认 orchestrator-mcp 已启用(绿点)
  3. 若没有,点 Refresh 或重启 Cursor

若仍看不到:Settings → MCP → Edit Config,确认项目级 .cursor/mcp.json 已加载。

方式 A(推荐,已写入项目):Cursor 自动拉起进程

{
  "mcpServers": {
    "orchestrator-mcp": {
      "command": ".../orchestrator-mcp/.venv/bin/python",
      "args": ["-m", "orchestrator_mcp"],
      "env": {
        "PYTHONPATH": ".../orchestrator-mcp/src",
        "ORCHESTRATOR_MCP_TRANSPORT": "stdio"
      }
    }
  }
}

方式 B:先 ./start.sh,再用 URL(需保持终端进程运行)

{
  "mcpServers": {
    "orchestrator-mcp": {
      "url": "http://127.0.0.1:18067/mcp"
    }
  }
}

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured