About
JoeAPI is a construction management platform that helps contractors and construction teams manage projects, clients, and business operations through an integrated system. Key capabilities include: - Client and contact management with CRM functionality - Project lifecycle management from proposals and estimates through completion - Action item tracking with supervisor assignments and schedule coordination - Financial monitoring with project summaries and detailed cost views - 18 pre-built workflows for common construction management tasks - 60+ API tools for CRUD operations on construction data The MCP server supports both cloud deployment via Smithery and local STDIO transport for development use.
Tools 26
list_clientsRetrieve a paginated list of clients
create_clientCreate a new client record
list_contactsRetrieve a list of contacts
create_contactCreate a new contact
list_proposalsGet a minimal list of proposals with optional project filtering. Returns only name, id, and projectId for each proposal. Use discover or search to find proposals and get full details.
list_estimatesGet a minimal list of estimates with optional project filtering. Returns only name, id, and projectId for each estimate. Use get_estimates to retrieve full details for a specific project's estimates.
list_action_itemsGet a minimal list of action items with optional project filtering. Returns only name (title), id, and projectId for each action item. Use get_action_item to retrieve full details for a specific action item.
get_action_itemGet full details for a specific action item by ID
create_action_itemCreate a new Action Item. Can be Generic (ActionTypeId=3), Cost Change (ActionTypeId=1), or Schedule Change (ActionTypeId=2). For Cost/Schedule changes, you MUST include the corresponding nested object with all required fields.
add_action_item_commentAdd a comment to an action item
assign_action_item_supervisorAssign a supervisor to an action item
list_projectsGet a minimal list of all projects. Returns only name, id, and projectId for each project. Use get_project to retrieve full details for a specific project.
get_projectGet full project details by project ID
get_scheduleGet full schedule data for a specific project
list_schedulesGet a minimal list of schedules with optional project filtering. Returns only name, id, and projectId for each schedule.
get_estimatesGet full estimate data for a specific project
discoverDiscover comprehensive project data by searching for a project and retrieving all related information including project details, financials (estimates, job balances, cost variance), schedules, and action items - all in one unified JSON response
asyncDelegate complex multi-step workflows to the async-agent system with real-time progress updates. Use this for tasks that require multiple coordinated steps, data gathering from multiple sources, or complex orchestration.
get_financialsGet comprehensive financial data for a project including job balances and cost variance
get_transactionsGet transaction list for a project with optional date range filtering
find_projectSearch for projects by name, client name, or other attributes. Returns matching projects with basic info.
find_estimateSearch for estimates and estimate categories. Can search across all estimates or within a specific project.
find_scheduleSearch for schedules and construction tasks. Can search across all schedules or within a specific project.
find_proposalSearch for proposals by proposal number, title, or description. Can optionally filter by project.
find_action_itemsSearch for action items by title or description. Can optionally filter by project.
searchGeneric search tool that can search across multiple entity types with optional filtering by project.
README
JoeAPI MCP Server
Model Context Protocol (MCP) server for JoeAPI construction management system. Exposes construction management tools to Claude and other AI assistants.
Overview
This MCP server provides:
Architecture
mcp/
├── index.ts # Main MCP server (Smithery + STDIO)
├── local-server.ts # STDIO transport runner
├── claude-desktop-config.example.json # Claude Desktop config
├── README.md # This file
└── server.ts # Legacy (deprecated)mcp-build/ # Compiled JavaScript (production)
├── index.js # Compiled server
├── local-server.js # Compiled STDIO runner
└── *.d.ts # TypeScript definitions
Deployment Options
1. Smithery (Cloud) - EXISTING
Your MCP server is already deployed on Smithery for cloud access.
Access: Via Smithery marketplace
URL: https://smithery.ai/server/@your-username/joeapi
Transport: HTTP
Use case: Remote access, team collaboration
2. Local STDIO - THIS SETUP
Run MCP server locally on your machine for development/testing.
Transport: STDIO (Standard Input/Output) Use case: Local development, faster iteration, offline work
---
Local STDIO Setup
Prerequisites
1. JoeAPI running locally:
npm run dev # Start JoeAPI on http://localhost:8080
2. Build MCP server:
npm run mcp:build
3. Configure Claude Desktop:
- Copy mcp/claude-desktop-config.example.json
- Update the command path to match your installation
- Add to Claude Desktop config
Option A: Development Mode (TypeScript)
For rapid development with auto-recompile:
npm run mcp:local
This runs tsx mcp/local-server.ts - TypeScript executed directly (no build needed).
Option B: Production Mode (Compiled JavaScript)
For production use:
# Build once
npm run mcp:buildRun compiled version
npm run mcp:start
This runs node mcp-build/local-server.js - faster startup, production-ready.
---
Claude Desktop Configuration
Step 1: Find Claude Config Directory
macOS:
~/Library/Application Support/Claude/
Windows:
%APPDATA%\Claude\
Linux:
~/.config/Claude/
Step 2: Edit claude_desktop_config.json
{
"mcpServers": {
"joeapi-local": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/joeapi/mcp-build/local-server.js"
],
"env": {
"JOEAPI_BASE_URL": "http://localhost:8080"
},
"disabled": false
}
}
}
Important:
~/ or ./)/ABSOLUTE/PATH/TO/joeapi/ to your actual path/Users/joe/dev/joeapi/mcp-build/local-server.jsStep 3: Restart Claude Desktop
Close and reopen Claude Desktop. The MCP server will connect automatically.
Step 4: Verify Connection
In Claude Desktop, type:
Can you use the find_workflow tool?
If connected, Claude will have access to all JoeAPI tools.
---
Available Tools
Workflow Discovery (ALWAYS START HERE!)
find_workflow - Discover pre-built workflows
autoExecute: false to see ALL 18 workflowsautoExecute: true with workflow name to get step-by-step instructions18 Pre-Built Workflows
1. win_loss_rate - Calculate proposal win/loss statistics
2. sales_pipeline - Analyze active proposals in pipeline
3. work_in_process_report - WIP report for active projects
4. job_costing_detail - Detailed job costing analysis
5. project_profitability - Profit analysis by project
6. cost_variance_analysis - Actual vs. estimated cost variance
7. cash_flow_forecast - Project cash flow projections
8. schedule_variance_analysis - Schedule delays and impacts
9. client_portal_update - Generate client progress updates
10. subcontractor_performance - Analyze subcontractor metrics
11. material_tracking - Track material costs and usage
12. labor_productivity - Analyze labor efficiency
13. cost_per_square_foot - Calculate $/sqft by trade
14. change_order_tracking - Track change orders/revisions
15. upgrade_pricing - Price client upgrade requests
16. update_schedule - Extend/adjust project schedules
17. plan_takeoff - Estimate from building plans
18. estimate_from_previous - Create estimate from past job
60+ Individual Tools (Categories)
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support