MCP Request Tracker logo

MCP Request Tracker

Manage Request Tracker tickets through MCP, including search, assignment, status changes, replies, time tracking, and checklist workflows.

Install MCP Request Tracker

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-request-tracker": {
      "command": "uvx",
      "args": [
        "mcp-request-tracker-crunchtools"
      ],
      "env": {
        "RT_URL": "YOUR_VALUE_HERE",
        "RT_USER": "YOUR_VALUE_HERE",
        "RT_PASS": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

MCP Request-tracker connects AI agents to Request Tracker (RT) for ticket search, inspection, creation, updates, communication, assignment, and resolution. Its tools support RT query syntax, ticket history, ownership and status changes, time tracking, private comments, and requester-visible replies. A weekly checklist workflow combines ownership, opening, correspondence, time entry, completion notes, and resolution into one operation. Reach for it when an agent needs to perform support and service-management work directly in an RT instance.

Use cases

  • Search RT tickets with query syntax
  • Take ownership of new support tickets
  • Reply to requestors and add private notes
  • Record work time and resolve completed tickets
  • Complete weekly checklist tickets in one workflow

Key features

  • RT query-based ticket search
  • Ticket history and assignment management
  • Status, queue, subject, and priority updates
  • Private comments and requester-visible replies
  • Set or add time worked
  • Combined weekly checklist completion workflow

Tools17

What MCP Request Tracker lets your agent do. Expand a tool for its parameters.

Verified live~1.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

10/10 checks healthy over the last 51d

What it can do

From the 17 tools this server returned when we ran it; 5 declare their own safety hints.

Read-only tools · 17
Network at startup2 connections
Files written at startup30

Observed 2026-10-20 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · mcp-request-tracker-crunchtools (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit2d agoMost recent push to the default branch.
Tools exposed17Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How MCP Request Tracker works

What MCP Request-tracker does

MCP Request-tracker exposes Request Tracker ticket operations through the Model Context Protocol. It covers the main stages of an RT workflow: finding tickets, reading ticket details and history, taking or assigning work, changing status, recording time, communicating with requestors, creating tickets, and resolving completed work.

Search uses RT query syntax, including conditions on status, owner, subject, queue, and creation date. The server can also retrieve open tickets assigned to a user and list new, unassigned tickets, with optional queue filtering.

A dedicated weekly checklist operation packages a recurring sequence into one workflow. It takes ownership of the ticket, opens it, adds the checklist results as correspondence, records time when supplied, adds a completion comment, and resolves the ticket.

How it works

The server connects to an RT instance using its base URL and credentials supplied through environment variables. MCP clients invoke individual ticket tools or the combined checklist workflow. Available operations distinguish between private internal notes and correspondence visible to the requestor, which supports both internal updates and external replies.

Ticket-management tools include ownership changes, status changes, opening, taking, resolving, and field updates for subject, priority, and queue. Time can either be replaced with a total value or increased by an additional amount. Resolution can optionally include a comment, while ticket creation supports opening new work in RT.

The server is designed to avoid exposing credentials in logs or errors. Password values use secret handling, credentials are removed from error messages, and the server does not read or write files or execute shell commands.

Setup and configuration

Install the package with uvx mcp-request-tracker-crunchtools or with pip:

Terminal
pip install mcp-request-tracker-crunchtools

A container image is also available:

bash
podman run -e RT_URL=... -e RT_USER=... -e RT_PASS=... quay.io/crunchtools/mcp-request-tracker

Set these required variables before starting the server:

  • RT_URL: the base URL of the RT instance.
  • RT_USER: the RT username.
  • RT_PASS: the RT password.

For an RT deployment protected by HTTP Basic Authentication, also set RT_HTTP_USER and RT_HTTP_PASS.

Claude Code can register the server with claude mcp add, passing the RT variables through --env and launching the package with uvx, or by running the container with standard input enabled. The project also documents development commands for dependency installation, tests, linting, and type checking with uv.

Tools and capabilities

The available tool groups are:

  • Search and retrieval: search tickets with RT query syntax, get ticket details, view ticket history, find a user's open tickets, and list new tickets.
  • Ticket changes: set an owner, change status, open a ticket, take ownership and open it, update subject, priority, or queue, and resolve a ticket.
  • Time tracking: set total time worked or add time to the existing total.
  • Communication: add a private comment or send requester-visible correspondence.
  • Creation and workflows: create tickets and complete weekly checklist tickets through the combined workflow.

The implementation is intended for Linux, macOS, and Windows, and is licensed under AGPL-3.0.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about MCP Request Tracker

MCP Request-tracker is an MCP server that connects AI agents to Request Tracker (RT) for ticket operations. Its tools search and inspect tickets, manage ownership and status, create and update tickets, record time, add private notes or requester-visible replies, and run a weekly checklist completion workflow.

Install it with `uvx mcp-request-tracker-crunchtools` or `pip install mcp-request-tracker-crunchtools`. You can also run the published container image with Podman and pass the RT connection variables through the environment.

MCP Request-tracker needs `RT_URL`, `RT_USER`, and `RT_PASS` to connect to RT. If the RT endpoint uses HTTP Basic Authentication, also set `RT_HTTP_USER` and `RT_HTTP_PASS`.

Yes, it can set the total time worked or add time to an existing total, then resolve a ticket with an optional comment. The weekly checklist workflow can also record supplied time before adding a completion comment and resolving the ticket.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Request Tracker AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-request-tracker?style=directory)](https://allmcps.com/mcp/mcp-request-tracker)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-request-tracker"><img src="https://allmcps.com/api/badge/mcp-request-tracker?style=directory" alt="MCP Request Tracker on AllMCPs" /></a>