- Home
- MCP servers
- JoeAPI
JoeAPI
- javascript
1
GitHub Stars
javascript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You can think of the JoeAPI MCP Server as a bridge between your JoeAPI construction management data and AI assistants like Claude. It exposes a rich set of pre-built workflows and direct API tools, all accessible through local STDIO or cloud-based Smithery deployments. This allows you to automate common construction tasks, retrieve up-to-date project information, and integrate AI-driven insights into your workflows.
How to use
You connect to the MCP server from your preferred MCP client. If you are using a cloud deployment, you access it via the Smithery marketplace and communicate over HTTP. For local development and testing, you run the local STDIO transport so the MCP server talks to you through Standard Input/Output on your machine.
Start by discovering available workflows. Use the find_workflow tool to list the 18 pre-built workflows and, if you want to see all details, set autoExecute to false. When you know a workflow name, you can trigger it and Claude will guide you through each step. You can also call any of the 60+ individual tools to read or mutate data directly in JoeAPI.
How to install
Prerequisites: you need Node.js installed, and JoeAPI must be running for the MCP server to connect to data.
Install JoeAPI dependencies and start JoeAPI server locally
npm install npm run dev
Build and run the MCP server locally in STDIO mode
npm run mcp:build npm run mcp:start
## Local STDIO setup notes
Use the local STDIO transport to run the MCP server on your machine. Claude Desktop will connect to the local server using STDIO.
Two key commands you’ll use during development are shown here for convenience.
Option A: Development mode (TypeScript)
npm run mcp:local
Option B: Production mode (compiled JavaScript)
# Build once
npm run mcp:build
# Run compiled version
npm run mcp:start
Claude Desktop configuration and connection
You connect Claude Desktop to the local MCP server by adding a config entry that points to the compiled local server. Use absolute paths and set the base URL so Claude knows where to send requests.
Example Claude Desktop config entry
{ "mcpServers": { "joeapi-local": { "command": "node", "args": [ "/ABSOLUTE/PATH/TO/joeapi/mcp-build/local-server.js" ], "env": { "JOEAPI_BASE_URL": "http://localhost:8080" }, "disabled": false } } }
## Environment variables
Set the base URL for JoeAPI in Claude Desktop and optionally supply an API key and user ID if JoeAPI requires authentication.
Required
JOEAPI_BASE_URL=http://localhost:8080
Optional (if JoeAPI requires auth)
JOEAPI_API_KEY=your_api_key
JOEAPI_USER_ID=1
Troubleshooting
If the MCP server isn’t connecting, verify JoeAPI is running, ensure the MCP server has been built, and check Claude Desktop logs for errors. You can also test the local MCP server manually to confirm it starts and responds.
Development tips
If you want to extend JoeAPI with new tools or workflows, edit the MCP source, rebuild, and restart Claude Desktop so the new capabilities appear to your AI assistant.
Available tools
find_workflow
Discover pre-built workflows. Set autoExecute to false to see all 18 workflows; set autoExecute true with a workflow name to execute it step-by-step.
win_loss_rate
Workflow to calculate proposal win/loss statistics.
sales_pipeline
Workflow to analyze active proposals in the sales pipeline.
work_in_process_report
Workflow to generate a WIP report for active projects.
job_costing_detail
Workflow for detailed job costing analysis.
project_profitability
Workflow to analyze profitability by project.
cost_variance_analysis
Workflow to analyze actual vs estimated cost variance.
cash_flow_forecast
Workflow to project cash flow projections.
schedule_variance_analysis
Workflow to assess schedule delays and their impacts.
client_portal_update
Workflow to generate client progress updates.
subcontractor_performance
Workflow to analyze subcontractor metrics.
material_tracking
Workflow to track material costs and usage.
labor_productivity
Workflow to analyze labor efficiency.
cost_per_square_foot
Workflow to calculate $/sqft by trade.
change_order_tracking
Workflow to track change orders and revisions.
upgrade_pricing
Workflow to price client upgrade requests.
update_schedule
Workflow to extend or adjust project schedules.
plan_takeoff
Workflow to estimate from building plans.
estimate_from_previous
Workflow to create an estimate from a past job.
Clients CRUD
Create, read, update, and delete client records.
Contacts CRUD
Manage client contacts.
SubContractors CRUD
Manage subcontractor records.
Proposals CRUD
Create and track proposals.
Estimates CRUD
Manage project estimates.
ProjectManagements CRUD
Manage active project data.