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
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.