kamai-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@kamai-mcpshow my construction projects and blueprints"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
kamai-mcp
Kamai's MCP server: tools and MCP Apps widgets for Kamai construction-blueprint projects, blueprints and takeoffs. It runs against Kamai's MCP API and validates access tokens issued by Kamai's OAuth authorization server. It holds no Kamai secrets.
Tools
Tool | What it does |
| Interactive panel of the user's projects and blueprints |
| A blueprint page with its take-off shapes drawn on top |
| Measured take-off quantities as a sortable table |
| Per-element rows (rooms, walls, doors, windows, objects) with outlines |
| Create or rename a project |
| Processing jobs of a project |
| Upload panel for a blueprint PDF |
| Import a PDF attached to a ChatGPT message |
| Open the Kamai app in a panel |
list_projects, get_project, get_blueprint, request_blueprint_upload and
finalize_blueprint_upload are app-only: callable by the widgets, not advertised to
the model.
Related MCP server: Estimaite MCP Server
Run locally with your API key
The quickest way to run this server against your own Kamai data is local mode: the host spawns the server, talks to it over stdio, and the credential is a personal API key from Kamai (API Keys in the Kamai app) instead of OAuth.
bun install
bun run build:widgets
KAMAI_API_KEY=... MCP_API_BASE_URL=https://mcp-api.kamai.io bun run localClaude Code:
claude mcp add --env KAMAI_API_KEY=... --env MCP_API_BASE_URL=https://mcp-api.kamai.io \
--transport stdio kamai -- bun /path/to/kamai-mcp/src/local.tsClaude Desktop (claude_desktop_config.json):
{ "mcpServers": { "kamai": {
"command": "bun", "args": ["/path/to/kamai-mcp/src/local.ts"],
"env": { "KAMAI_API_KEY": "...", "MCP_API_BASE_URL": "https://mcp-api.kamai.io" } } } }The key is used as the bearer for every API call; the tools run as the key's owner.
Run the HTTP server
bun install
cp .env.example .env
bun run devThe values in .env.example are placeholders: set MCP_PUBLIC_URL and
MCP_AUTH_ISSUER to your tunnel and to a reachable authorization server before
starting, or every request will be refused with invalid_token.
Variable | Meaning |
| Listen port, default 8006 |
| The URL hosts call and ask a token for (the |
| Issuer of the access tokens, matched byte for byte against the token's |
| Optional. Defaults to |
| Kamai MCP API base URL, |
| Optional comma-separated audiences, for a cutover. Defaults to |
| Local mode only: the personal API key the tools run as |
| Optional comma-separated extra origins |
The MCP API and the authorization server are operated by Kamai, so running the
HTTP server end to end needs access to both. An MCP server is only really testable
against a real host, and a host can only reach a public HTTPS URL, so HTTP-mode
development means running behind a tunnel and pointing MCP_PUBLIC_URL at it.
bun run dev builds the widgets first: the server serves the built HTML from
dist/widgets/, not the React source, so rebuild after touching anything under
src/widgets/app/.
The widgets use React, TypeScript, Vite, Tailwind CSS, DaisyUI and Lucide. Vite produces one self-contained HTML resource per widget, so nothing needs hosting.
Local builds require Bun 1.3.3 and Node.js 22.12 or newer.
Layout
src/index.ts HTTP server, OAuth protected-resource metadata, MCP transport
src/local.ts stdio entrypoint for local mode (personal API key)
src/auth.ts Bearer-token verification (RFC 9728 challenges)
src/server.ts Tool and resource registration
src/api.ts Client for the Kamai MCP API
src/elements.ts list_elements paging, filtering and result budgeting
src/widgets/ Widget resources, CSP metadata and the React widget sourcesContributing
See CONTRIBUTING.md. Security issues go to the address in SECURITY.md, not to the issue tracker.
License
Apache-2.0. Copyright 2026 Kamai Enterprises LTD.
The Kamai name and logo are trademarks of Kamai Enterprises LTD and are not covered by the license.
This server cannot be deployed
Maintenance
Related MCP Connectors
- AgineraOAuthai.aginera
Turn construction drawings into takeoffs, measured routes, schedules and estimates.
Read-only access to Cogram projects, meetings, emails, RFIs and drawings for AEC teams
1Construction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate.
Explore and analyze Cupix construction site data: 360 images, progress, and insights.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceConnects AI assistants to JoeAPI construction management system, enabling management of clients, contacts, proposals, estimates, action items, project schedules, and financial data through natural language.1-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to perform construction takeoff and estimating from drawing PDFs, including upload, scale calibration, trade-based takeoff, pricing, and proposal export.MIT
- FlicenseNot gradedqualityCmaintenanceProvides read-only MCP tools to query building construction approval lifecycle data, covering project discovery, bidding, contracts, drawing review, permits, and completion records.1-

co.geztio/platformofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to search and manage construction project economic data, including unit price analyses, resource catalogs, budget trees, and price lists, with secure multi-tenant access.MIT