mcpField
R
Runhooks

Runhooks

Local
runhooks.appCloud & Infra0Updated 1w ago
RepositoryVisit website

About Runhooks

Runhooks is a local MCP server for AI agents that schedule and manage one-off or recurring HTTP jobs through the Runhooks API. Its tools also cover execution history, replay, usage, and failure alerts.

Key features

  1. 01Create cron or interval jobs
  2. 02List and manage scheduled jobs
  3. 03Pause and resume jobs
  4. 04View and replay executions
  5. 05Manage failure alerts

Use cases

  1. 01Schedule recurring HTTP requests
  2. 02Set up a one-off HTTP job
  3. 03Replay a past job execution
  4. 04Receive alerts for job failures

MCP support

Runs locally and connects MCP clients to the Runhooks REST API over HTTPS. It exposes tools for creating and managing jobs, executions, usage, accounts, and alerts.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "runhooks-runhooks": {
      "command": "npx",
      "args": [
        "-y",
        "@runhooks/mcp"
      ],
      "env": {
        "RUNHOOKS_API_KEY": "<RUNHOOKS_API_KEY>",
        "RUNHOOKS_API_URL": "<RUNHOOKS_API_URL>"
      }
    }
  }
}
Run commandnpx -y @runhooks/mcp
Environment variables to set
RUNHOOKS_API_KEYSecretRunhooks API key (rh_live_...). Required for all tools except provision_account; get one instantly with the provision_account tool, the dashboard, or the CLI.
RUNHOOKS_API_URLAPI origin override. Defaults to https://api.runhooks.app.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@runhooks/mcp0.1.10

Tools

18

Saved tool list · updated 6d ago

ParameterTypeRequiredDescription
namestringNoOptional display name for the account

Details

From the project README

@runhooks/mcp

Model Context Protocol (MCP) server for Runhooks — reliable HTTP scheduling infrastructure. It lets AI agents (Claude Desktop, Cursor, and any MCP client) schedule and manage recurring and one-off HTTP jobs directly.

The server runs locally on your machine: your MCP client spawns it with npx and it talks to the Runhooks REST API over HTTPS. There is no hosted service — just this package.

Install

Add it to your MCP client config. For Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "runhooks": {
      "command": "npx",
      "args": ["-y", "@runhooks/mcp"],
      "env": { "RUNHOOKS_API_KEY": "rh_live_..." }
    }
  }
}

No API key yet? Leave env out and ask the agent to run the provision_account tool once — it creates an instant account (no email), returns an rh_live_... key, and saves it locally to ~/.runhooks/mcp.json. The key is reused automatically from then on, so every other tool works immediately with no restart and no need to provision again. (Setting RUNHOOKS_API_KEY is still the most portable option across machines, and it always takes precedence over the saved key.)

Verify

Check the server starts and advertises its tools (replace the key, or omit env and use provision_account from inside your client):

RUNHOOKS_API_KEY=rh_live_... npx -y @runhooks/mcp

Environment variables

VariableDescriptionDefault
RUNHOOKS_API_KEYYour API key (rh_live_...). Optional — provision_account saves a key locally if unset. Takes precedence over the saved key.—
RUNHOOKS_API_URLAPI origin.https://api.runhooks.app

Tools

ToolDescription
provision_accountCreate an anonymous account and get an API key (no email).
whoamiShow the current account.
rotate_keyRotate the API key.
create_jobCreate a scheduled job (cron or interval).
list_jobsList jobs with filters and pagination.
get_jobGet one job by ID.
update_jobUpdate a job.
delete_jobDelete a job.
pause_job / resume_jobPause or resume a job.
list_executionsList a job's run history.
replay_executionRe-run a past execution.
get_usageShow plan usage and limits.
list_alerts / create_alert / get_alert / update_alert / delete_alertManage failure alerts (email, webhook, Slack).

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.