# Runhooks [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/runhooks/runhooks-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 1495  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/runhooks

## Description
Schedule and manage recurring and one-off HTTP jobs on Runhooks from your AI agent.

## Tools
Capabilities this server exposes over MCP:

- **provision_account** — Create a new anonymous Runhooks account (no email required) and save its API key locally for reuse. Idempotent: if this server already has a key (from RUNHOOKS_API_KEY or a previous provision), it returns the EXISTING account instead of creating a duplicate. Call this at most once — never to recover from an auth error.
- **whoami** — Show the currently authenticated Runhooks account (name, plan, API key prefix).
- **rotate_key** — Rotate the API key. The old key stops working immediately; the new key is returned, saved locally, and used for the rest of this session.
- **create_job** — Create a new scheduled job — an HTTP request fired on a schedule. The schedule.type is one of: "cron" (schedule.expression is a cron string, e.g. "0 9 * * 1,4" for every Monday & Thursday at 09:00 — build/preview expressions at https://runhooks.app/tools/cron-expression-builder; optional IANA schedule.timezone), "interval" (schedule.expression is the number of milliseconds between runs, as a string), or "once" for a single future run (schedule.expression is an ISO-8601 date-time — either an absolute instant like "2026-12-25T14:00:00Z"/with offset, or a naive wall-clock time like "2026-12-25T09:00:00" interpreted in schedule.timezone, defaulting to UTC; the time must be in the future). One-off jobs support the same retries, alerts and logs as recurring jobs.
- **list_jobs** — List your scheduled jobs with optional filters and pagination.
- **get_job** — Get a single job by its ID.
- **update_job** — Update an existing job. Only the fields you provide are changed.
- **delete_job** — Delete a job permanently.
- **pause_job** — Pause a job — it stops executing until resumed.
- **resume_job** — Resume a paused job.
- **list_executions** — List recent executions (run history) for a job.
- **replay_execution** — Re-run a past execution immediately.
- **get_usage** — Show the current plan usage and limits for the account.
- **list_alerts** — List your failure-alert configurations.
- **create_alert** — Create a failure alert. Fires when a job dead-letters. Channel is email, webhook, or slack.
- **get_alert** — Get a single alert configuration by its ID.
- **update_alert** — Update an alert configuration. Only the fields you provide are changed.
- **delete_alert** — Delete an alert configuration.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "runhooks": {
    "command": "npx",
    "args": ["-y","@runhooks/mcp"],
    "env": {
      "RUNHOOKS_API_KEY": "",
      "RUNHOOKS_API_URL": ""
    }
  }
}
```

**Requires environment variables:** `RUNHOOKS_API_KEY`, `RUNHOOKS_API_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Runhooks MCP server does

Runhooks MCP server gives an MCP client access to Runhooks HTTP scheduling infrastructure. Agents can create recurring or one-off HTTP jobs, then inspect and manage those jobs through the same interface. Scheduling supports cron and interval patterns.

The tool set also covers the surrounding operational tasks. Agents can list jobs with filters and pagination, retrieve or update an individual job, delete jobs, and pause or resume them. Execution history can be listed, and a previous execution can be replayed. Account tools expose the current identity, API-key rotation, and anonymous account provisioning. Usage information includes plan limits, while alert tools manage failure notifications through email, webhooks, or Slack.

## How it works

The package runs locally on the machine where the MCP client launches it. A client starts the server with `npx -y @runhooks/mcp`; the process then communicates with the Runhooks REST API over HTTPS. There is no hosted MCP process to connect to.

Authentication uses a Runhooks API key. If `RUNHOOKS_API_KEY` is set, the server uses that value. Without it, an agent can call `provision_account` to create an anonymous account without an email address. The resulting `rh_live_...` key is saved locally in `~/.runhooks/mcp.json` and reused by later tool calls. The environment variable takes precedence over the saved key.

## Setup and configuration

Add the package as a command-based MCP server in the client configuration. A typical entry uses `npx` as the command and passes `-y` and `@runhooks/mcp` as arguments. The API key can be supplied through the server's environment configuration, or account provisioning can be performed from the client after startup.

`RUNHOOKS_API_KEY` supplies the Runhooks API key and is optional when local key storage is available. `RUNHOOKS_API_URL` changes the API origin; its default is `https://api.runhooks.app`. To verify startup independently, run the package with `npx -y @runhooks/mcp`, optionally setting `RUNHOOKS_API_KEY`, and confirm that the client can discover its tools.

## Tools and capabilities

- Provision an anonymous account, inspect the current account, or rotate its API key.
- Create, list, retrieve, update, delete, pause, and resume scheduled jobs.
- Configure jobs with cron or interval schedules.
- Review execution history and replay a previous execution.
- Check plan usage and limits.
- Create, list, retrieve, update, and delete failure alerts for email, webhook, or Slack destinations.

The package is intended for MCP clients such as Claude Desktop and Cursor, as well as other clients that support MCP server processes.

_Full upstream README: https://allmcps.com/mcp/runhooks/readme_