经 AI Skill Hub 精选评估,智能估算平台 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
智能估算平台 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
智能估算平台 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/braedonsaunders/bidwright
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "bidwright"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 智能估算平台 执行以下任务... Claude: [自动调用 智能估算平台 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"______": {
"command": "npx",
"args": ["-y", "bidwright"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="./bidwright-readme.png" alt="Bidwright construction estimating platform" width="100%" /> </p>
<p align="center"> <a href="https://github.com/braedonsaunders/codeflow"><img src=".github/codeflow-card.svg" alt="Bidwright codebase stats — powered by codeflow" width="100%" /></a> </p>
<p align="center"> <strong>The estimating platform that runs the whole bid — intake, knowledge, takeoff, pricing, scheduling, review, and quote delivery — on top of an AI agent that actually has hands.</strong> </p>
<p align="center"> Drop the bid package. Index the spec. Take off the drawings <em>and</em> the model. Parameterize the assemblies. Price it with real burdens. Let the agent review it. Send the branded quote. </p>
| Area | Live capabilities |
|---|---|
| Package intake | Upload bid packages, unzip archives, classify files, extract text from PDFs, spreadsheets, and text files, preserve tables and key-value structure. |
| Knowledge | Books, documents, datasets, cabinets (org or project scoped), hybrid pgvector search, persona binding, page browsing. |
| Estimating workspace | Projects, quotes, revisions, worksheets, line items, phases, modifiers, conditions, summary rows, notes, lead letters, report sections, activity history, cross-project performance views. |
| Assemblies | Parameterized kits, nested sub-assemblies, quantity expressions, per-component overrides, worksheet snapshotting. |
| 2D takeoff | PDF viewer, scale calibration, count/linear/area annotations, symbol detection, multi-page counts, region "Ask AI", markup export. |
| 3D model takeoff | Element hierarchy ingestion, per-element quantities, BOM generation, revision diffing, worksheet links with multipliers. |
| Scheduling | Tasks, milestones, SS/SF/FS/FF dependencies, calendars, resources, baselines, Gantt views tied to estimate phases. |
| Pricing | Catalogs, tiered rate schedules, labour cost tables, burden periods, travel policies, entity categories, customers, departments, conditions. |
| Quote output | Revision compare, package preview, branded PDF generation with configurable layouts and sections, email delivery. |
| AI & agents | Multi-provider models, 150+ tools, local Ollama embeddings, MCP server, Claude Code / Codex runtime sessions, plugin framework. |
| Quote review | Agent-driven coverage / gap / risk / competitiveness analysis with evidence-linked findings and calibration feedback. |
| Multi-tenant ops | Organizations, users, super-admin setup, org switching, brand profiles, brand capture from website crawl, estimator personas, data import/export, admin flows. |
Drop in a plugin with a config schema and tool definitions, and it shows up in the agent's tool registry and the UI. Every execution is tracked (input, formstate, output, applied line items) so plugins are auditable, not magic.
高质量的开源MCP工具,具有较强的实用价值
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
AI Skill Hub 点评:智能估算平台 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | bidwright |
| Topics | aiconstructionestimating |
| GitHub | https://github.com/braedonsaunders/bidwright |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间:2026-06-24 · 更新时间:2026-06-24 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端