Roster
Enables querying your team's work (stats, overdue, workload, active members, etc.) via natural language, scoped to your department with read-only signed-token access.
README
roster-cli-mcp
Query your team's work from the terminal, or straight from Claude. A small CLI and MCP server for Roster. No app, no SQL.
$ roster stats
team size: 7
open: 24 done: 37 overdue: 5
active now: 2
Install
git clone https://github.com/brickshubkuwait/roster-cli-mcp.git
cd roster-cli-mcp
npm install
Set your token, then run anything:
export ROSTER_TOKEN=<your token>
node cli.mjs stats # or: npm link → roster stats
Need a token? Ask your admin to issue one.
CLI
| Command | What it shows |
|---|---|
roster stats |
Team dashboard — size, open / done / overdue, who's tracking |
roster team |
Your team members |
roster overdue |
Cards past their due date and not done |
roster workload |
Open + overdue cards per person |
roster active |
Who's tracking time right now |
roster comments |
Recent comments on your team's cards |
roster search "<text>" |
Find cards by title or client |
roster card <id> |
One card in detail (first 8 chars of the id) |
Run roster help to see them all. Full reference: QUERIES.md.
Use it from Claude (MCP)
Add this to your Claude config (~/.claude.json → mcpServers), then ask in plain
English — "what's overdue for my team?", "who's overloaded?":
{
"mcpServers": {
"roster": {
"command": "node",
"args": ["/path/to/roster-cli-mcp/mcp.mjs"],
"env": { "ROSTER_TOKEN": "<your token>" }
}
}
}
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.