The setup script will: 1. Create a virtual environment 2. Install all dependencies (including dashboard) 3. Prompt for your SQL Server connection
Most developer tooling work still happens through a UI a human drives. Hangfire MCP MCP server moves it into the conversation instead. The setup script will: 1. Create a virtual environment 2. Install all dependencies (including dashboard) 3. Prompt for your SQL Server connection string (or read from .vscode/mcp.json) 4. Create VS Code MCP configuration 5. Test the.
hangfire-mcp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 14 tools. What each one is for:
Cron — 0 */5 * * * (every 5 minutes)Queue — defaultlist_jobs — List jobs by state (Enqueued, Processing, Succeeded, Failed, etc.)get_job — Get detailed job info including arguments and exception detailsget_job_history — Get the state history of a jobretry_job — Retry a failed jobdelete_job — Delete a jobrequeue_job — Move a job back to queuelist_recurring_jobs — List all recurring jobs with cron schedulesget_recurring_job — Get recurring job detailstrigger_recurring_job — Run a recurring job immediatelypause_recurring_job — Pause scheduled executionsConfiguration is passed through the environment: HANGFIRE_CONNECTION_STRING. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Hangfire MCP's toolset — Cron, Queue, list_jobs and 11 more — is a fair guide to whether it matches your workflow. It is maintained by inansen; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Cron | 0 */5 * * * (every 5 minutes) |
| Queue | default |
| list_jobs | List jobs by state (Enqueued, Processing, Succeeded, Failed, etc.) |
| get_job | Get detailed job info including arguments and exception details |
| get_job_history | Get the state history of a job |
| retry_job | Retry a failed job |
| delete_job | Delete a job |
| requeue_job | Move a job back to queue |
| list_recurring_jobs | List all recurring jobs with cron schedules |
| get_recurring_job | Get recurring job details |
| trigger_recurring_job | Run a recurring job immediately |
| pause_recurring_job | Pause scheduled executions |
| resume_recurring_job | Resume a paused job |
| get_stats | Server statistics (succeeded, failed, processing counts) |
{
"mcpServers": {
"hangfire": {
"command": "uvx",
"args": ["hangfire-mcp"],
"env": {
"HANGFIRE_CONNECTION_STRING": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| HANGFIRE_CONNECTION_STRING | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.