MCP — Use BuildWorkPro from your AI agent
The Model Context Protocol (MCP) is Anthropic’s open standard for connecting large language models to external tools and data. An MCP-aware client — Claude, Claude Code, ChatGPT, Grok Bot, OpenClaw, Hermes Agent, your own agent — speaks one protocol, and any MCP server (BuildWorkPro included) can plug in. The model gets structured access to your records, with scoped permissions, instead of you copy-pasting screenshots into a chat.
What you get
Section titled “What you get”The BuildWorkPro MCP server exposes the same domain you already use through the REST API, packaged for LLMs:
- 295 tools across bids, projects, contacts, leads, pay applications, change orders, invoices, site logs, time entries, products, documents, messaging, calendar, webhooks, and identity. Read your contacts, leads, bids, projects, pay applications, change orders, time entries, site logs, products, documents, webhooks, and team members. Create new records and drive workflow steps (send a bid, accept a bid, approve a pay app, approve a change order).
- 7 resources (
bid://,project://,contact://,lead://,payapp://,changeorder://, andsitelog://URI schemes) that let the model fetch a single record by id with one round trip and pin it into context. - 11 prompts the model can call by name to compose useful workflows, including
draft_bid_followup,summarize_open_projects,weekly_status_report,draft_lead_followup,explain_pay_app_math, andpipeline_weekly_summary.
Tools are scoped. Listing contacts requires contacts:read; creating a bid requires bids:write; sending a bid requires bids:send. The full inventory is in the Tools catalog.
How authentication works
Section titled “How authentication works”The server uses OAuth 2.1 with Dynamic Client Registration (RFC 7591) — the same flow Zapier uses. You don’t paste an API key into your AI client. Instead:
- The MCP client (Claude, ChatGPT, Grok Bot, and the rest) registers itself with BuildWorkPro automatically the first time you connect.
- You’re redirected to the BuildWorkPro authorize page in your browser.
- You see a consent screen listing the exact scopes the AI is requesting, with the ones that can approve money flagged, and you approve or deny the request.
- The client receives a refresh token and exchanges it for short-lived access tokens.
Your AI assistant gets only the scopes it asked for and you approved. Revoke access at any time from Settings -> Authorized apps.
Two install paths
Section titled “Two install paths”- Streamable HTTP (recommended). The hosted endpoint at
https://app.buildworkpro.com/api/mcpworks with any modern MCP client. No local process to run, no Node.js to install. This is the path documented in the install guides below. - stdio (local development only). A local Node.js process speaks MCP over stdin/stdout. Useful when you’re hacking on the server itself or running on a machine without internet access. We don’t recommend this for everyday use.