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.
A Model Context Protocol (MCP) server for managing Hangfire background jobs directly from VS Code Copilot and other MCP-compatible clients. Monitor job queues, retry failed jobs, manage recurring tasks, and view real-time statistics — all without leaving your editor.
Job Management: List, view, retry, delete, and requeue jobs
Recurring Jobs: List, view, trigger, pause, and resume recurring jobs
Statistics: View server stats, queues, and active servers
Auto-Discovery: Automatically finds connection strings from appsettings.json
Web Dashboard: Built-in web UI with real-time stats and job management
Related MCP server: Nall.Hangfire.Mcp
# Clone the repo
git clone https://github.com/inansen/hangfire-mcp.git
cd hangfire-mcp
# Run cross-platform setup (Windows, macOS, Linux)
python setup.pyThe setup script will:
Create a virtual environment
Install all dependencies (including dashboard)
Prompt for your SQL Server connection string (or read from .vscode/mcp.json)
Create VS Code MCP configuration
Test the connection
Optionally start the dashboard
pip install hangfire-mcpOr with uvx:
uvx hangfire-mcpAdd to your VS Code settings (settings.json):
{
"mcp": {
"servers": {
"hangfire-mcp": {
"command": "uvx",
"args": ["hangfire-mcp", "--workspace", "${workspaceFolder}"]
}
}
}
}Create .vscode/mcp.json in your project:
{
"servers": {
"hangfire-mcp": {
"command": "uvx",
"args": ["hangfire-mcp", "--workspace", "${workspaceFolder}"]
}
}
}Use ODBC-style connection strings:
{
"servers": {
"hangfire-mcp": {
"command": "python",
"args": ["-m", "hangfire_mcp", "--workspace", "${workspaceFolder}"],
"env": {
"HANGFIRE_CONNECTION_STRING": "Driver={ODBC Driver 17 for SQL Server};Server=localhost;Database=Hangfire;UID=sa;PWD=yourpassword;Encrypt=no;"
}
}
}
}Note: This project uses
pyodbcand requires ODBC-format connection strings, not ADO.NET format.
The server finds connection strings in this priority order:
--connection-string CLI argument
HANGFIRE_CONNECTION_STRING environment variable
Auto-discover from ${workspaceFolder}/**/appsettings*.json
User config at ~/.config/hangfire-mcp/connections.json (Linux/macOS) or %APPDATA%\hangfire-mcp\connections.json (Windows)
Use the configure tool to set it manually
Tool | Description |
| List jobs by state (Enqueued, Processing, Succeeded, Failed, etc.) |
| Get detailed job info including arguments and exception details |
| Get the state history of a job |
| Retry a failed job |
| Delete a job |
| Move a job back to queue |
Tool | Description |
| List all recurring jobs with cron schedules |
| Get recurring job details |
| Run a recurring job immediately |
| Pause scheduled executions |
| Resume a paused job |
Tool | Description |
| Server statistics (succeeded, failed, processing counts) |
| List queues with pending job counts |
| List active Hangfire servers |
Tool | Description |
| Set connection string for current workspace |
In VS Code Copilot Chat:
User: Show me failed jobs
Agent: [calls list_jobs(state="Failed")]
Found 3 failed jobs:
| ID | State | Job Type | Created | Reason |
|----|-------|----------|---------|--------|
| 123 | Failed | OrderSyncJob.Execute | 2026-03-17 10:30 | Connection timeout |
| 124 | Failed | EmailJob.Send | 2026-03-17 10:45 | SMTP error |
User: Retry job 123
Agent: [calls retry_job(job_id=123)]
Job 123 has been requeued to 'default' queue.
User: When did CacheRefreshJob last run?
Agent: [calls get_recurring_job(job_id="CacheRefreshJob")]
Recurring Job: CacheRefreshJob
- Cron: 0 */5 * * * (every 5 minutes)
- Last Run: 2026-03-17 12:55:00
- Queue: default
User: Trigger CacheRefreshJob now
Agent: [calls trigger_recurring_job(job_id="CacheRefreshJob")]
CacheRefreshJob has been triggered. New job ID: 456The package includes a built-in web dashboard for visual job management.
pip install hangfire-mcp[dashboard]# Windows
.\scripts\run-dashboard.ps1
# macOS / Linux
chmod +x scripts/run-dashboard.sh
./scripts/run-dashboard.sh
# Or manually (any platform)
export HANGFIRE_CONNECTION_STRING="Driver={ODBC Driver 17 for SQL Server};Server=localhost;Database=Hangfire;..."
python -m uvicorn hangfire_mcp.dashboard:app --host 127.0.0.1 --port 8080Open http://127.0.0.1:8080 in your browser.
Real-time Stats: Succeeded, Failed, Processing, Enqueued, Scheduled counts
Job List: View all jobs with filtering by state
Job Actions: Retry, Delete, View details with one click
Recurring Jobs: Pause, Resume, Trigger recurring jobs
Server Status: Online/Idle/Offline status based on heartbeat
Auto-refresh: Updates every 10 seconds
Python 3.11+
SQL Server with Hangfire database
ODBC Driver 17 for SQL Server (or compatible)
# Clone the repository
git clone https://github.com/inansen/hangfire-mcp.git
cd hangfire-mcp
# Install all dependencies
pip install -e ".[dev]"
# Run tests
pytestFork the repository
Create a feature branch (git checkout -b feature/my-feature)
Commit your changes (git commit -am 'Add my feature')
Push to the branch (git push origin feature/my-feature)
Open a Pull Request
MIT
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Hacker News MCP server for ChatGPT, Claude and any AI agent: list upvoted items, list hidden items, list favorites, list my comment threads, get an item with its comments, favorite an item and hide an item in your own Hacker News account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Hacker News yourself; Cotlet does not store your password and you need no Hacker News API key. About the official Hacker News API: Hacker News has an official API, but it is read-only and public (checked 28 Oct 2026). It returns items, users and the story lists. Setup and FAQ: https://cotlet.dev/integrations/hacker-news-api-mcp-server
Jobber MCP server for ChatGPT, Claude and any AI agent: create quote, convert quote to job, create invoice, send invoice and list unpaid invoices in your own Jobber account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Jobber yourself; Cotlet does not store your password and you need no Jobber API key. About the official Jobber API: Yes, Jobber has a GraphQL API in its Developer Center (checked 14 Oct 2026), but you cannot use it without registering an app. Each Jobber account authorizes your app with OAuth 2.0 and tokens must be refreshed. Setup and FAQ: https://cotlet.dev/integrations/jobber-api-mcp-server
PeoplePerHour MCP server for ChatGPT, Claude and any AI agent: search projects, get project brief, search freelancers, get freelancer profile, search Offers, get Offer, list categories and get account in your own PeoplePerHour account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to PeoplePerHour yourself; Cotlet does not store your password and you need no PeoplePerHour API key. About the official PeoplePerHour API: PeoplePerHour has no public API and no developer docs (checked 12 Oct 2026). Projects, freelancers and Offers are searched and read in the website only, and the one built-in alert is an email, instant or daily, from up to 10 saved searches. Setup and FAQ: https://cotlet.dev/integrations/peopleperhour-api-mcp-server
Mindbody MCP server for ChatGPT, Claude and any AI agent: list classes, get class roster, search clients, get client visits, list client contracts, book client into class, cancel client booking and add client in your own Mindbody account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Mindbody yourself; Cotlet does not store your password and you need no Mindbody API key. About the official Mindbody API: Yes. Mindbody has a Public API v6, but it is for approved developers, each studio owner must activate access for their site, and it has no official MCP server (checked 5 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/mindbody-api-mcp-server
