WorkBuddy Quotation MCP
Provides a quotation/quote-pricing MCP server for WorkBuddy, enabling querying pricing sources (org_api), securing JWT sessions, and supporting tools like lock-code and B-price lookups while keeping runtime isolated from Mixing.
README
WorkBuddy 报价旁路包(PC · GitHub 优先 · 与 Mixing 隔离)
仓库: https://github.com/JASMINE145-ACT/workbuddy-quote-pack (私有)
交付方式: 员工git clone后用 WorkBuddy 打开本仓库根目录(若在 monorepo 内则为workbuddy-quote-pack子目录)。
WorkBuddy 会读AGENTS.md+.mcp.json(仍需员工填密钥并批准 MCP)。
非目标: iOS;打进 Mixing NSIS。
员工步骤
1. 安装 Bun(PATH 或 %LOCALAPPDATA%\.bun\bin\bun.exe)— dist 必须用 Bun,不能用 Node
2. git clone https://github.com/JASMINE145-ACT/workbuddy-quote-pack.git
3. WorkBuddy 打开该仓库根目录
4. pip install -r requirements.txt(建议 Python 3.11)
5. MCP env:ORG_USERNAME + LLM_SELECTOR_API_KEY + LLM_SELECTOR_BASE_URL + LLM_SELECTOR_MODEL
6. 无 monorepo:设 CCB_REPO_ROOT,或 IT 跑 stage-runtime-from-repo.ps1 → runtime/
排障见 TROUBLESHOOTING.md(Bun vs Node、stdout 污染、selector 环境变量等)。
首次登录:
$env:ORG_USERNAME = "<user>"
$env:ORG_PASSWORD = "<pass>"
python .\ensure-org-session.py
python .\smoke-org-api-source.py
# → source=org_api
详细清单见 REQUIREMENTS.md。
WorkBuddy 会读什么
| 文件 | 作用 |
|---|---|
AGENTS.md |
项目级助手说明(指向 system-prompt) |
.mcp.json |
项目 MCP:quotation → start-quotation-mcp.ps1 |
system-prompt.md |
完整查价 SOP |
ALLOWED_TOOLS.md |
工具白名单(含库存) |
env.example |
环境变量说明(无密钥) |
requirements.txt |
Python 依赖 |
TROUBLESHOOTING.md |
Connection closed / Bun / selector 清单 |
不会自动出现的: org 密码、selector key、Accurate AOL_* —— 必须员工自配。
运行时(无 CCB 安装)
start-quotation-mcp.ps1 解析顺序:
- 本目录
runtime/(IT 可用stage-runtime-from-repo.ps1生成,勿提交 token) - 已装的 CCB-Wanding(一般没有)
- 上层 monorepo(
RepoRoot/ 默认D:\Projects\claude-code-best)
推荐:员工直接 clone 含本目录的 monorepo(或 sparse checkout),这样不必 stage zip。
架构
WorkBuddy 打开本目录
→ AGENTS.md + .mcp.json
→ start-quotation-mcp.ps1
· ensure org JWT → %LOCALAPPDATA%\CCB-Wanding\workbuddy\
· PRICE_LKG_DIR 隔离
· 进程级 selector / AOL
→ quotation-server stdio → source=org_api
IT / 仓库维护
- 本包只改
ccb-installer/workbuddy-quote-pack/(+ 本 task 文档);禁止改 Mixing agent / NSIS。 - zip(
pack-zip.ps1)仅作离线备份,不是主交付。 - 推 GitHub:私有仓即可;不要提交
.org-session.token/.env/ 真实 key(已在.gitignore)。
验收
smoke-org-api-source.py→source=org_api- 无 selector → start 报
Missing selector key - WorkBuddy 聊天「直接50」→ 锁码 + B 价(配齐 key 后)
Rollback
删 %LOCALAPPDATA%\CCB-Wanding\workbuddy\ + 卸项目 MCP。不影响 Mixing。
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.