The Float MCP server is an archived community project that provides comprehensive integration with Float.com's resource management platform through the Model Context Protocol, enabling AI assistants to perform project management, resource allocation, time tracking, and team coordination operations.
Core Capabilities:
Team & People Management - Full CRUD operations on team members, departments, roles, and accounts with permissions and access controls
Project Management - Complete project lifecycle management including phases, milestones, tasks, dependencies, and custom status workflows
Resource Allocation - Schedule team member assignments, manage capacity planning, and track resource utilization
Time Tracking - Log billable/non-billable hours, manage timesheets, time-off requests with approval workflows, and holiday management
Client Management - Maintain client database with associated projects and filtering
Reporting & Analytics - Generate time reports, project reports, utilization metrics, capacity analysis, budget variance, and billable analysis with flexible grouping and filtering
Bulk Operations - Efficiently create multiple entries at once (time off, project tasks, logged time) and bulk update permissions
Technical Features:
4 Optimized Decision-Tree Tools - Consolidated entity management through
manage-entity,manage-project-workflow,manage-time-tracking, andgenerate-reportBackward Compatibility - All original 100+ granular tools remain available alongside optimized tools
Advanced Integration - Built-in rate limiting with exponential backoff, TypeScript/Zod validation, comprehensive logging, Docker containerization, and pagination support (up to 200 items)
Full MCP Compliance - Complete Model Context Protocol integration for AI assistants like Claude
Supports deployment and containerization through Docker with production-ready configuration and Docker Compose support for running the Float MCP server.
Uses environment variable configuration for API keys, logging levels, and other settings through .env file support.
Hosted on GitHub with releases, issue tracking, and discussions for community support and contributions.
Built on Node.js runtime environment requiring version 22.0.0 or later for execution.
Distributed and managed through npm package manager for installation and dependency management.
Plans to support optional Redis caching layer for enhanced performance in future roadmap.
Implemented in TypeScript with full type safety and comprehensive type definitions throughout the codebase.
Supports Yarn package manager as an alternative to npm for dependency installation and management.
Uses Zod schema validation library for runtime type checking and API response validation ensuring data integrity.
Click on "Install 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., "@float-mcpshow me my team's time logged this week"
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.
๐ฆ This project is now archived
Float has released their own first-class MCP server, and we're archiving this community project in favor of it. Float has the resources and direct API access to continue this work far better than we can.
A huge thank you to the community for the contributions, feedback, and support โ and to the Float team for embracing MCP natively. ๐
๐ Use Float's official MCP server going forward: float.com/whats-new/float-mcp-ask-float-in-chatgpt-or-claude
Float MCP Server
A comprehensive Model Context Protocol (MCP) server that provides seamless integration with Float.com - the resource management and project planning platform. This server exposes Float's complete API as MCP tools, enabling AI assistants like Claude to interact with Float for project management, resource allocation, time tracking, and team coordination.
Related MCP server: MarineTraffic MCP Server
๐ Features
Complete Float API Coverage
๐ฅ People Management - Full CRUD operations for team members
๐ Project Management - Projects, phases, tasks, and milestones
โฑ๏ธ Time Tracking - Logged time, timesheets, and billable hours
๐ Resource Allocation - Team member assignments and scheduling
๐ฏ Task Management - Project tasks, dependencies, and workflows
๐ข Organization - Departments, roles, accounts, and permissions
๐ Time Off - PTO requests, approvals, and holiday management
๐ Reports - Time reports, utilization, and project analytics
Advanced Features
๐ Rate Limiting - Built-in API rate limiting with exponential backoff
๐ก๏ธ Type Safety - Full TypeScript support with Zod schema validation
๐ Comprehensive Logging - Detailed logging for debugging and monitoring
โก Performance - Optimized for fast response times and efficient API usage
๐งช Testing - Comprehensive integration test suite
๐ณ Docker Support - Ready-to-deploy Docker container
๐ Quick Start
Prerequisites
Node.js 22.0.0 or later
Float.com account with API access
Valid Float API key
1. Installation Options
A. DXT Extension (Recommended)
For DXT-compatible environments, download the latest DXT package:
๐ฆ Download Float MCP Extension (.dxt)
Install the .dxt file through your DXT-compatible application.
B. Manual Installation
# Using npm
npm install
# Using yarn
yarn install2. Configuration
Create a .env file in the project root:
# Float API Configuration
FLOAT_API_KEY=your_float_api_key_here
FLOAT_API_BASE_URL=https://api.float.com/v3
# Optional: Enable debug logging
LOG_LEVEL=info3. Build & Run
# Build the project
npm run build
# Start the MCP server
npm start
# For development with auto-reload
npm run dev4. MCP Client Integration
For DXT Installation
After installing the DXT extension, configure your Float API key in the extension settings. The extension will handle the MCP server configuration automatically.
For Manual Installation
Add to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"float-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"FLOAT_API_KEY=YOURAPIKEY",
"-e",
"LOG_LEVEL=debug",
"ghcr.io/asachs01/float-mcp:latest"
]
}
}
}๐ Available Tools
The Float MCP server provides 4 optimized decision-tree tools that efficiently replace 246+ granular tools while maintaining complete functionality:
๐ง Optimized Tools (Recommended)
1. manage-entity - Core Entity Management
Consolidates all CRUD operations for core entities with decision tree routing:
manageEntity({
entity_type: "people" | "projects" | "tasks" | "clients" | "departments" | "roles" | "accounts" | "statuses",
operation: "list" | "get" | "create" | "update" | "delete" | "get-current-account" | "bulk-update-account-permissions",
// ... entity-specific parameters
})Replaces: All CRUD tools for people, departments, roles, accounts, projects, tasks, clients, and statuses (~120 tools)
2. manage-project-workflow - Project Operations
Handles all project-specific workflow operations:
manageProjectWorkflow({
workflow_type: "phases" | "milestones" | "project-tasks" | "allocations",
operation: "list" | "get" | "create" | "update" | "delete" | "complete" | "archive" | "bulk-create" | "reorder",
// ... workflow-specific parameters
})Replaces: Project phases, milestones, project tasks, allocations, dependencies, bulk operations (~60 tools)
3. manage-time-tracking - Time Management
Manages all time-related operations with comprehensive reporting:
manageTimeTracking({
tracking_type: "logged-time" | "timeoff" | "public-holidays" | "team-holidays",
operation: "list" | "get" | "create" | "update" | "delete" | "approve" | "reject" | "bulk-create",
report_type?: "person-summary" | "project-summary" | "timesheet" | "billable-analysis",
// ... time-specific parameters
})Replaces: Logged time, time off, holidays, approvals, timesheets, summaries (~45 tools)
4. generate-report - Analytics & Reporting
Comprehensive reporting and analytics engine:
generateReport({
report_type: "time-report" | "project-report" | "people-utilization-report" | "capacity-report" | "budget-report",
// Advanced filtering and grouping options
group_by?: "person" | "project" | "client" | "department" | "date" | "week" | "month",
include_details?: boolean,
// ... extensive reporting parameters
})Replaces: All reporting tools with advanced analytics, grouping, filtering (~20 tools)
๐ Optimization Benefits
๐ฅ Massive Efficiency: 246+ tools โ 4 optimized tools (98.4% reduction)
๐ง AI-Friendly: Decision tree parameters instead of tool proliferation
โก Better Performance: Consolidated API calls and reduced overhead
๐ Full Compatibility: Zero functionality loss, complete backward compatibility
๐ ๏ธ Easier Maintenance: Centralized logic with consistent patterns
๐ Legacy Tools (Backward Compatibility)
All original 246+ granular tools remain available for backward compatibility:
Reporting & Analytics
Reports:
get-time-report,get-project-report,get-people-utilization-reportAnalytics:
get-person-logged-time-summary,get-project-logged-time-summary
๐ง Configuration
Environment Variables
Variable | Description | Required | Default |
| Your Float API key | โ Yes | - |
| Float API base URL | โ No |
|
| Logging level ( | โ No |
|
| Maximum API retry attempts | โ No |
|
| API request timeout (ms) | โ No |
|
Getting a Float API Key
Log in to your Float account
Go to Settings > API > Personal Access Tokens
Click Generate New Token
Copy the API key
Add it to your
.envfile
๐ Usage Examples
Basic Operations
// List all projects
const projects = await listProjects({});
// Get a specific project
const project = await getProject({ project_id: 12345 });
// Create a new person
const person = await createPerson({
name: 'John Doe',
email: 'john@example.com',
department_id: 1,
});
// Schedule an allocation
const allocation = await createAllocation({
project_id: 12345,
people_id: 67890,
start_date: '2024-01-15',
end_date: '2024-01-31',
hours: 8,
});Advanced Workflows
// Get team utilization report
const utilization = await getPeopleUtilizationReport({
start_date: '2024-01-01',
end_date: '2024-12-31',
});
// Bulk create project tasks
const tasks = await bulkCreateProjectTasks({
project_id: 12345,
tasks: [
{ name: 'Design Phase', start_date: '2024-01-01' },
{ name: 'Development Phase', start_date: '2024-01-15' },
],
});
// Process time off request
await createTimeOff({
people_ids: [67890],
timeoff_type_id: 1,
start_date: '2024-02-01',
end_date: '2024-02-05',
status: 1, // Pending approval
});
await approveTimeOff({
timeoff_id: 123,
approved_by: 456,
notes: 'Approved for vacation',
});๐งช Testing
Running Tests
# Run all tests
npm test
# Run integration tests (requires API key)
npm run test:integration
# Run tests with coverage
npm run test:coverage
# Run specific test suites
npm run test:integration:mock # Mock API responses
npm run test:integration:real # Real API calls (use with caution)Test Configuration
For integration tests with real API calls:
# .env.test
FLOAT_API_KEY=flt_your_test_api_key
TEST_REAL_API=true
TEST_MOCK_MODE=false๐ณ Docker Support
Using Docker
# Build the image
docker build -t float-mcp .
# Run the container
docker run -d \
--name float-mcp \
-e FLOAT_API_KEY=your_float_api_key_here \
-p 3000:3000 \
float-mcpDocker Compose
version: '3.8'
services:
float-mcp:
build: .
environment:
- FLOAT_API_KEY=your_float_api_key_here
- LOG_LEVEL=info
ports:
- '3000:3000'
restart: unless-stopped๐ Troubleshooting
Common Issues
API Key Issues
Error: Unauthorized (401)
# Solution: Check your API key format and validityRate Limiting
Error: Too Many Requests (429)
# Solution: The server automatically handles rate limiting with exponential backoffConnection Issues
Error: Network timeout
# Solution: Check your internet connection and Float API statusDebug Mode
Enable detailed logging:
LOG_LEVEL=debugThis will show all API requests/responses and internal operations.
๐ค Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
Development Setup
# Clone the repository
git clone https://github.com/asachs01/float-mcp.git
cd float-mcp
# Install dependencies
npm install
# Set up environment
cp .env.example .env
# Edit .env with your Float API key
# Run in development mode
npm run devCode Quality
# Run linting
npm run lint
# Format code
npm run format
# Type checking
npm run typecheck๐ Documentation
API Documentation - Complete API reference
Tool Reference - Detailed tool documentation
Usage Guide - Usage patterns and examples
Integration Testing - Testing guide
Claude Integration - Claude Desktop setup
๐ Project Status
โ Complete Float API Coverage - All Float v3 endpoints implemented
โ Production Ready - Full error handling, rate limiting, and logging
โ Well Tested - Comprehensive integration test suite
โ Type Safe - Full TypeScript with Zod validation
โ Docker Ready - Production-ready containerization
โ MCP Compatible - Full Model Context Protocol compliance
๐บ๏ธ Roadmap
Float API v4 Support - When released by Float
Enhanced Caching - Optional Redis caching layer
Webhook Support - Real-time Float event notifications
Bulk Operations - Enhanced bulk import/export tools
Custom Reports - Advanced reporting and analytics
Multi-tenant Support - Multiple Float account support
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Support
๐ Documentation: See the docs directory
๐ Bug Reports: GitHub Issues
๐ฌ Discussions: GitHub Discussions
๐ท๏ธ Tags
float mcp model-context-protocol project-management resource-management time-tracking typescript api-integration claude ai-tools
Built with โค๏ธ for the Float and MCP communities