ticket-tracker
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-workflow-agent
A small Model Context Protocol server that exposes a SQLite ticket tracker as tools, plus an intake agent that reads sample requests, classifies them, files tickets, and writes a summary.
The agent talks to Claude through the Anthropic API when ANTHROPIC_API_KEY is set. Without a key it uses a deterministic mock classifier, so the workflow and the tests run fully offline.
What this covers
A SQLite ticket store: create, list, get, update status, and summarize counts
An MCP server (official Python SDK) that exposes those operations as tools over stdio
An intake workflow that reads JSON or CSV requests, classifies them, files tickets, and writes a Markdown or JSON summary
Retries with exponential backoff around the classifier
Structured JSON logs on stderr
Dry-run and mock modes so you can run the workflow without writing tickets or calling an API
Unit tests, including in-memory MCP client calls and a flaky-provider retry test
GitHub Actions: lint and pytest on every push and pull request
Related MCP server: mcp-issue-tracker
Architecture
flowchart LR
Incoming["Incoming requests<br/>JSON or CSV"] --> Agent["Workflow agent"]
Agent -->|classify| Provider["Claude or mock provider"]
Agent -->|create / list / update / summarize| Store["Ticket store"]
Store --> DB[("SQLite")]
Agent --> Summary["Run summary<br/>Markdown or JSON"]
Desktop["Claude Desktop"] -->|stdio| Server["MCP server"]
Server --> StoreThe MCP server and the workflow agent share the same store. Claude Desktop never needs the agent process; it calls the tools directly. The agent can run as a batch job without a desktop host.
Quick start
git clone https://github.com/harkaransingh44-stack/mcp-workflow-agent.git
cd mcp-workflow-agent
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytestRequires Python 3.11 or newer.
Run the intake workflow in mock mode (no API key):
python -m ticketflow.agent_cli --provider mock --out reports/summary.mdDry-run (classify only, do not write tickets):
python -m ticketflow.agent_cli --provider mock --dry-run --out reports/summary.mdUse the sample CSV instead of the JSON file:
python -m ticketflow.agent_cli --input data/incoming_requests.csv --provider mockWith a live Claude key:
export ANTHROPIC_API_KEY=sk-ant-...
# optional: export ANTHROPIC_MODEL=claude-sonnet-5-5
python -m ticketflow.agent_cli --provider anthropic --out reports/summary.mdMCP tools
Tool | What it does |
| Create a ticket ( |
| List tickets, optionally filtered by |
| Set a ticket to |
| Return counts by status, priority, and category |
Category values: access, billing, bug, feature, incident, other.
Priority values: low, medium, high, urgent.
Connect to Claude Desktop
Install this project into a virtualenv as shown above.
Edit the Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the server, using absolute paths to this repo and to the venv's Python:
{
"mcpServers": {
"ticket-tracker": {
"command": "/ABSOLUTE/PATH/TO/mcp-workflow-agent/.venv/bin/python",
"args": ["-m", "ticketflow.server"],
"cwd": "/ABSOLUTE/PATH/TO/mcp-workflow-agent",
"env": {
"TICKET_DB_PATH": "/ABSOLUTE/PATH/TO/mcp-workflow-agent/data/tickets.db"
}
}
}
}Restart Claude Desktop. Ask it to "create a high-priority incident ticket about the portal being down, then summarize open tickets."
Start the server yourself only when you want to confirm it boots (it will wait on stdin and print nothing):
python -m ticketflow.serverTICKET_DB_PATH defaults to data/tickets.db under this repo.
Project layout
.
├── data/
│ ├── incoming_requests.json # Sample inbox for the agent
│ └── incoming_requests.csv # Same idea, CSV shape
├── src/ticketflow/
│ ├── store.py # SQLite backend
│ ├── server.py # MCP tools over stdio
│ ├── llm.py # Mock and Anthropic providers
│ ├── retries.py # Backoff helper
│ ├── logging_config.py # JSON logs
│ ├── workflow.py # Classify → file → summarize
│ └── agent_cli.py # Command-line entry point
├── tests/
└── .github/workflows/tests.ymlConfiguration
Variable | Default | Purpose |
|
| SQLite file used by the MCP server |
| unset | Enables the live Claude provider |
|
| Model id for the live provider |
|
| Override provider selection |
CI
On every push and pull request to main, GitHub Actions installs the package, runs ruff, then runs pytest with the mock provider. JUnit and HTML reports are uploaded as artifacts. No Anthropic key is required in CI.
Author
Harkaran Singh LinkedIn: linkedin.com/in/harkaran-singh784
License
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Project tracker for AI agents and teams: file, claim, update and hand off tickets over MCP.
Customer support for MCP servers: work your tickets from Claude or any MCP client. Service key auth.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
File, find and update AoTwin tickets from your AI assistant, and hand one to AoTwin when you ask.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI assistants like Cursor to manage customer support tickets in SQLite through MCP tools, supporting creation, retrieval, search, and updates via natural language.4-
- AlicenseNot gradedqualityDmaintenanceEnables interaction with a local SQLite-backed issue tracker, offering full CRUD operations (search, fetch, summarize, create, comment, close/reopen) with team-scoped visibility, authorization, rate limiting, and audit logging.MIT
- AlicenseBqualityCmaintenanceProvides a local-first MCP interface for managing SQLite-backed projects, boards, and tickets, including metrics, epics, documentation links, run-history, and staging-lease coordination with completion summaries for done items.32MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to manage a local SQLite task backlog over stdio, with tools to create, search, list, get, update, and stat tasks while preserving audit history and idempotency.MIT