mcp-server-smartsheet-rm
MCP server for Smartsheet Resource Management (10,000ft API). It enables AI agents to orchestrate time tracking, resource scheduling, projects, leaves, expenses, and custom fields.
README
๐ mcp-server-smartsheet-rm
Enterprise Model Context Protocol (MCP) server for Resource Management by Smartsheet (10,000ft API).
Enables AI coding agents, planners, and assistants (Claude, Cortex, Antigravity, VS Code) to orchestrate the complete Smartsheet RM REST API surface: time tracking & timesheet reconciliation, resource scheduling & allocations, capacity planning, project & phase management, leaves/holidays, expense tracking, and custom fields.
โก Tool Surface Overview
The server exposes tools covering projects, resources, timesheets, and capacity:
- Default Registration: 98 tools (with bulk-destructive operations gated by default).
- With Bulk Operations: 100 total tools when
SMARTSHEET_RM_ALLOW_BULK_DESTRUCTIVE=1. - Read-Only Mode: 39 tools (
readOnlyHint=true). - Destructive Gates: 21 tools requiring explicit
confirm=True(19 standard + 2 bulk). - Idempotent Operations: 4 tools with
idempotentHint=true.
Domain Breakdown
Counts below include the 2 bulk-destructive tools (100 total).
- Time Tracking & Approvals (8 tools): List/get/create/update/delete time entries, fetch suggestions, approve/reject hours, lock timesheets.
- Projects & Phases (11 tools): Full CRUD for projects, project users, milestones, budgets, and project phases.
- Assignments & Scheduling (5 tools): Full CRUD for resource assignments, percentages, fixed hours, and schedules.
- Users, Roles & Capacity (17 tools): User management, bill rate tiers, availability queries, utilization metrics, roles, and disciplines.
- Clients & Contacts (8 tools): Client organization CRUD and client contact records.
- Leaves & Holidays (10 tools): Vacation/PTO leave types, non-working days, and regional company holidays.
- Expense Tracking (8 tools): Expense submissions, category definitions, and billable tracking.
- Tags & Custom Fields (10 tools): Custom field definitions, field values, and tagging.
- Approvals, Statuses & Placeholders (9 tools): Organization approvals, user work status tracking (ITO/WFH/OOO/VAC), and placeholder resources.
- Subtasks, Reports & Webhooks (8 tools): Assignment task checklists, custom report generation (rows/totals), and event webhooks.
- Composite Workflow Recipes (6 tools): Bulk timesheet logging, auto-suggestion confirmation, 40h reconciliation audit, project schedule cloning, and bulk deletion.
๐ Quickstart & Installation
1. Installation
# Using uv (recommended)
uv pip install mcp-server-smartsheet-rm
# Or standard pip
pip install mcp-server-smartsheet-rm
2. Environment Variables
| Variable | Description | Default |
|---|---|---|
SMARTSHEET_RM_API_TOKEN |
Smartsheet RM (10,000ft) API Token (Required) | - |
SMARTSHEET_RM_BASE_URL |
Base API URL | https://api.rm.smartsheet.com/api/v1 |
SMARTSHEET_RM_PROFILE |
Tool profile subset: time, projects, admin, full |
full |
SMARTSHEET_RM_READONLY |
Set to 1 to restrict server to read-only tools |
0 |
SMARTSHEET_RM_ALLOW_BULK_DESTRUCTIVE |
Set to 1 to unlock bulk delete operations |
0 |
SMARTSHEET_RM_LOG_FORMAT |
Set to json for Datadog/CloudWatch structured logs |
text |
๐ป Client Configurations
Google Antigravity (~/.gemini/antigravity-cli/mcp_config.json)
{
"mcpServers": {
"smartsheet-rm": {
"command": "uvx",
"args": ["mcp-server-smartsheet-rm"],
"env": {
"SMARTSHEET_RM_API_TOKEN": "your-api-token"
},
"lazy": true
}
}
}
Snowflake Cortex (~/.snowflake/cortex/mcp.json)
{
"servers": {
"smartsheet-rm": {
"command": "uvx",
"args": ["mcp-server-smartsheet-rm"],
"env": {
"SMARTSHEET_RM_API_TOKEN": "your-api-token"
}
}
}
}
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"smartsheet-rm": {
"command": "uvx",
"args": ["mcp-server-smartsheet-rm"],
"env": {
"SMARTSHEET_RM_API_TOKEN": "your-api-token"
}
}
}
}
๐ก๏ธ Safety & Reliability
- Secret Redaction: API tokens, bearer headers, and sensitive keys are automatically scrubbed from errors and logs.
- Destructive Gates: Every deletion tool declares
confirm: bool = Falseand rejects execution unless the caller explicitly passesconfirm=True. - Profile Filtering: Minimize token footprint by loading only relevant tool sets (
time,projects,admin). - Resilience: Exponential backoff with randomized jitter on HTTP 429 rate limits.
๐งช Testing & Validation
# Run tests with 100% coverage requirement
pytest --cov=src/smartsheet_rm_mcp --cov-fail-under=100 -v
# Run Tool Contract verification
python scripts/check_tool_contract.py
# Run OpenAPI Drift check
python scripts/check_openapi_drift.py
<!-- mcp-name: io.github.christianclaudio/smartsheet-rm -->
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.