Manage construction punch lists programmatically via AI agents. Create, update, and track project defects and completion items with real-time progress monitoring for job sites.
io.github.vulkanr/lastbluetape-mcp
Local install
STDIO
1 required env var
How models use it and what it is built for.
Manage construction punch lists programmatically via AI agents. Create, update, and track project defects and completion items with real-time progress monitoring for job sites.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Your LastBlueTape API key for authentication (starts with lbt_)
Optional Stripe payment method ID (pm_xxx) for auto-upgrading lists to Pro
Where to find authoritative docs and source for LastBlueTape.
Paste any of these into Agent Studio after connecting LastBlueTape.
Common questions about connecting and running LastBlueTape.
What is LastBlueTape MCP used for?
It enables AI agents to programmatically create, manage, and track construction punch lists—lists of defects, incomplete work, or items requiring follow-up on job sites. You can add items, update status, and monitor project completion progress.
How do I authenticate with the LastBlueTape API?
Set the required LASTBLUETAPE_API_KEY environment variable with your API key (format: lbt_xxx). You can optionally add LASTBLUETAPE_PAYMENT_METHOD with a Stripe payment method ID (pm_xxx) to enable automatic Pro list upgrades.
Do I need a Stripe payment method configured?
No, LASTBLUETAPE_PAYMENT_METHOD is optional. It only enables automatic upgrades to Pro punch lists. Basic list creation and management work with just the API key.
How do I install and run this MCP server?
Install via npm with `npx @lastbluetape/mcp-server@1.0.1`, then set your LASTBLUETAPE_API_KEY environment variable. The server communicates over stdio, so connect it to your MCP client to start managing punch lists.
Can I track multiple punch lists for different projects?
Yes, the server supports creating and managing multiple punch lists. You can add items to different lists, track progress separately, and query status across all active projects.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams