MCP Request Tracker CrunchTools
Enables secure interaction with Request Tracker (RT) for ticket management, including search, creation, updates, resolution, time tracking, and workflow automation.
README
MCP Request Tracker CrunchTools
A secure MCP (Model Context Protocol) server for Request Tracker (RT) ticket management.
Features
- Secure Credential Handling: Passwords stored as SecretStr, never logged
- Full Ticket Management: Search, view, create, update, and resolve tickets
- Time Tracking: Track time worked on tickets
- Workflow Automation: Pre-built workflows like checklist completion
- Cross-Platform: Works on Linux, macOS, and Windows
Installation
Option 1: Using uvx (Recommended)
uvx mcp-request-tracker-crunchtools
Option 2: Using pip
pip install mcp-request-tracker-crunchtools
Option 3: Using Container
podman run -e RT_URL=... -e RT_USER=... -e RT_PASS=... quay.io/crunchtools/mcp-request-tracker
Configuration
Set the following environment variables:
| Variable | Required | Description |
|---|---|---|
RT_URL |
Yes | Base URL of your RT server |
RT_USER |
Yes | RT username |
RT_PASS |
Yes | RT password |
RT_HTTP_USER |
No | HTTP Basic Auth username |
RT_HTTP_PASS |
No | HTTP Basic Auth password |
Usage with Claude Code
Using uvx
claude mcp add mcp-request-tracker-crunchtools \
--env RT_URL=https://rt.example.com \
--env RT_USER=your_username \
--env RT_PASS=your_password \
-- uvx mcp-request-tracker-crunchtools
Using Container
claude mcp add mcp-request-tracker-crunchtools \
--env RT_URL=https://rt.example.com \
--env RT_USER=your_username \
--env RT_PASS=your_password \
-- podman run -i --rm -e RT_URL -e RT_USER -e RT_PASS quay.io/crunchtools/mcp-request-tracker
Available Tools
Search and View
search_tickets- Search tickets using RT query syntaxget_ticket- Get ticket detailsget_ticket_history- Get ticket history/changelogget_my_open_tickets- Get open tickets for a userget_new_tickets- Get new/unassigned tickets
Update Tickets
set_ticket_owner- Set ticket ownerset_ticket_status- Set ticket statusopen_ticket- Open a ticketresolve_ticket- Resolve/close a tickettake_ticket- Take ownership and open
Time Tracking
set_time_worked- Set total time workedadd_time_worked- Add time to existing time
Communication
add_ticket_comment- Add private comment (not visible to requestor)reply_to_ticket- Add correspondence (visible to requestor)
Creation
create_ticket- Create a new ticket
Workflows
complete_weekly_checklist- Complete a weekly checklist ticket with results
RT Query Syntax Examples
Status = 'new'
Status = 'open' AND Owner = 'scott'
Subject LIKE 'checklist'
Queue = 'Professional'
Created > '2025-01-01'
Owner = 'Nobody'
Security
This server is built with security in mind:
- SecretStr: Passwords are stored using Pydantic's SecretStr to prevent accidental logging
- Error Sanitization: Credentials are scrubbed from all error messages
- No Filesystem Access: The server never reads or writes files
- No Shell Execution: No subprocess or shell commands
- Minimal Dependencies: Only essential packages to reduce attack surface
- Automated CVE Scanning: Weekly security scans via GitHub Actions
- Container Security: Built on Hummingbird images with minimal CVE count
See SECURITY.md for the full security design document.
Development
# Clone the repository
git clone https://github.com/crunchtools/mcp-request-tracker.git
cd mcp-request-tracker
# Install dependencies
uv sync --all-extras
# Run tests
uv run pytest
# Lint
uv run ruff check src tests
# Type check
uv run mypy src
License
This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). See LICENSE for details.
<!-- mcp-name: io.github.crunchtools/request-tracker -->
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.
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.
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.
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.