opentakeoff
Open-source (AGPL-3.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. Rooms measured on the wall faces, symbol sweeps, materials + quantities with full provenance, built for preconstruction. Runs entirely in your browser.
No outside reports on file
Use this tool only with non-sensitive construction documents, verify all takeoffs manually before relying on them, and keep it on isolated machines without access to other company systems or networks.
Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesReads local filesNOTED
- Command executionNo shell command runner notedLOW
- Network reachFetches arbitrary web URLsREVIEW
- CredentialsNo API token requiredLOW
- Package sourcenpm (opentakeoff-mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y opentakeoff-mcpEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-27.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Opentakeoff
OpenTakeoff is an open-source tool that helps AI agents measure and extract material quantities from construction PDF documents. It works directly in your browser, letting an AI agent read floor plans, count rooms, identify materials, and generate takeoff reports (lists of what's needed to build something) without needing separate bolted-on plugins.
Who it’s for
Construction companies, flooring contractors, and preconstruction teams who want AI assistants to automatically analyze blueprints and estimate materials. It's designed for teams willing to run open-source tools and understand their limitations.
Alternatives
- Bluebeam Studio (commercial; built-in takeoff with machine learning for construction PDFs) - PlanGrid / Autodesk Construction Cloud (construction management platform with document and measurement tools) - Touchplan (visual construction planning; supports document imports) - Manual measurement plugins (commercial PDF readers with construction takeoff add-ons)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/Kentucky-ai/opentakeoff (opens external site) for installation. Likely involves cloning the repository and following setup instructions for browser-based deployment or adding it as an MCP server to Claude Desktop.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 716
- Weekly npm downloads
- 2.3k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- PDF injection attacks: A malicious PDF could contain specially crafted content designed to trick the AI into reporting false measurements or material counts. - No verification of accuracy: The tool's measurements depend entirely on PDF quality and AI interpretation; a bad scan or unusual floor plan could produce wildly wrong takeoffs. - Data exposure: Construction documents often contain sensitive site plans, budgets, and client information; running this tool could expose that data if logs or results aren't protected. - Supply chain trust: As an open-source project with moderate GitHub activity (704 stars), updates and security patches may lag behind risks discovered by users. - No audit trail: The tool may not create detailed logs showing exactly how it arrived at each measurement, making it hard to catch errors or trace problems.
How to lower the risk
Least-privilege permissions
- Run in a dedicated browser profile with no saved passwords or login credentials.
- Do not give the tool network access beyond what's needed to load your local PDFs.
Network isolation
- Use it only offline or on an isolated network if possible; block outbound connections.
- Never upload real client documents if the tool phones home (check the code).
Monitoring
- Keep logs of which PDFs you've analyzed and what outputs were generated.
- Spot-check results from the tool against manual measurements on a sample of projects.
Red flags to watch for
- Sudden changes in measurement accuracy or new features you didn't enable.
- Error messages or outputs that mention external APIs or cloud services.
- Missing or incomplete documentation about what data the tool stores.
Questions
How do I install Opentakeoff?
Run npx -y opentakeoff-mcp in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/Kentucky-ai/opentakeoff.
Are there security reports about Opentakeoff?
No reports found for this package in our research (last checked 2026-10-30). Opentakeoff currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include pdf injection attacks.
Is Opentakeoff actively maintained?
Opentakeoff has 716 GitHub stars and 2.3k weekly npm downloads. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/Kentucky-ai/opentakeoff before pinning it in production.
What are alternatives to Opentakeoff?
Notable alternatives to Opentakeoff include Bluebeam Studio. You can also compare Opentakeoff side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Opentakeoff? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/kentucky-ai-opentakeoff)HTML embed:
<a href="https://agentarmorhq.com/skills/kentucky-ai-opentakeoff"><img src="https://agentarmorhq.com/api/badge/kentucky-ai-opentakeoff" alt="AgentArmorHQ Risk Grade for Opentakeoff" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "kentucky-ai-opentakeoff"Share with your security lead
Need sign-off to use opentakeoff? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: opentakeoff
- **Listing URL:** https://agentarmorhq.com/skills/kentucky-ai-opentakeoff
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 716 GitHub stars, 2.3k weekly npm downloads
#### Permission & Blast-Radius Signals
- **Local files:** Reads local files
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** No API token required
- **Package source:** npm (opentakeoff-mcp)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts opentakeoff-mcp`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- Kentucky-ai
- Source code
- github.com/Kentucky-ai/opentakeoff
- Install command
- npm install opentakeoff-mcp
- Est. context load
- ~1.1k tokens / turn (~6 tool schemas, 0.55% of 200k context)
- Popularity
- 716 GitHub stars, 2.3k weekly npm downloads
- Last updated
- 2026-10-30
- Last graded
- 2026-10-27
Community
Discussions for Opentakeoff
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude