Estimaite MCP Server
Enables AI agents to perform construction takeoff and estimating from drawing PDFs, including upload, scale calibration, trade-based takeoff, pricing, and proposal export.
README
Estimaite MCP server
Construction takeoff and estimating for AI agents.
Estimaite reads a construction drawing PDF, measures and counts the scope on the sheet, prices it against editable material and labour rates, and returns an estimate. This repository holds the public manifest and connection docs for its remote MCP server, so an MCP client can drive the whole job: upload a plan set, set or auto-detect scale, take off by trade, price it, and export a priced estimate or proposal.
The server is hosted. There is nothing to install and no source in this repository.
Connect
Endpoint
https://mcp.esti-maite.com/mcp
Transport is streamable HTTP. Authentication is OAuth 2.1: the client opens a browser, you approve the connection against your Estimaite account, and the client stores the token. Any MCP client that supports remote servers with OAuth will work, including Claude and other MCP-capable assistants.
Claude Desktop / Claude Code
Add it as a remote MCP server pointing at the endpoint above and complete the browser approval when prompted.
What it can do
Roughly, and grouped the way an estimator works:
- Drawings — upload a plan set, list sheets, read a sheet, extract text and schedules from it
- Scale — calibrate from a known dimension, or auto-detect the plan scale
- Takeoff — count symbols, measure linear runs, areas and volumes, organise into layers by system, size and material, and audit a sheet for what was missed
- Estimating — price takeoffs against cost items, apply overhead and profit, and produce a proposal
- Projects — create and manage projects, clients and assignees, and read the bid board
The full tool reference is in docs/tools.md. A connected client lists the live tool set,
which is always the authoritative answer.
Trades
Nine, covering concrete and masonry, structural and misc steel, carpentry and framing, drywall, insulation and ceilings, HVAC and sheet metal, plumbing and fire protection, electrical and low voltage, finishes and roofing, and sitework and utilities. The method follows how each trade is actually taken off rather than one generic workflow.
Accuracy
Estimaite makes no published accuracy claim. Measurement accuracy is being evaluated on a small sample and no number is published, so none is asserted here. What the product does claim is structural: measurements are produced before an estimator opens the drawing, and the estimator reviews them against an overlay of what was measured.
In the MCP registry
Published as com.esti-maite/construction-takeoff-estimating, under a namespace verified against
esti-maite.com.
curl 'https://registry.modelcontextprotocol.io/v0/servers?search=construction-takeoff-estimating'
The entry is named for what the server does rather than for the brand because registry search matches the
server name and ignores the description. server.json in this repository is the manifest that was published.
Links
- Product: https://www.esti-maite.com
- How agents drive it: https://www.esti-maite.com/mcp
- About: https://www.esti-maite.com/about
- Support: support@esti-maite.com
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。