Skip to content
MCP server

Runhooks

Let an agent schedule cron, interval and one-off HTTP jobs on Runhooks

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally
Version
0.1.12
Listing updated
3 days ago

About Runhooks

Runhooks is a freemium MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Scheduling a webhook normally means writing code or clicking through a dashboard. Here the agent can do it from a prompt such as a POST to a sync endpoint every five minutes, or a one-time warm-up call on a chosen date. The package runs locally as a subprocess and calls the Runhooks REST API over HTTPS, so there is nothing to host.

Accounts can be created by the agent itself: provision_account makes an anonymous account without email and saves the key to ~/.runhooks/mcp.json, so the other tools work straight away. Eighteen tools cover jobs, run history with replay, usage, and failure alerts by email, webhook or Slack.

Usage counts against your Runhooks plan. The pricing page shows a Free tier (10 jobs, 2,000 runs a month, 24-hour log retention) and paid tiers from $19 a month with higher run, retention and concurrency limits.

Install

Run in a terminal

claude mcp add runhooks-mcp --env RUNHOOKS_API_KEY='<RUNHOOKS_API_KEY>' -- npx -y @runhooks/mcp

Add to claude_desktop_config.json

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

{
  "servers": {
    "runhooks-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@runhooks/mcp"
      ],
      "env": {
        "RUNHOOKS_API_KEY": "<RUNHOOKS_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Configuration

  • RUNHOOKS_API_KEYRunhooks 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.

Tools this server provides (18)

Taken from the project documentation; the running server may differ.

create_job
Create a recurring (cron or interval) or one-off scheduled job.
list_jobs
List jobs with filters and pagination.
get_job
Get one job by ID.
update_job
Update an existing job.
delete_job
Delete a job.
pause_job
Pause a job.
resume_job
Resume a job.
list_executions
List a job's run history.
replay_execution
Re-run a past execution immediately.
provision_account
Create an anonymous account and return an API key.
whoami
Show the current account.
rotate_key
Rotate the API key.
get_usage
Show plan usage and limits.
list_alerts
List failure-alert configurations.
create_alert
Create a failure alert by email, webhook or Slack.
get_alert
Get one alert by ID.
update_alert
Update an alert.
delete_alert
Delete an alert.

What it does

Cron and interval jobs
Create recurring HTTP jobs or one-off runs at a future time.
Run history and replay
List a job's executions and re-run a past one.
Failure alerts
Configure alerts by email, webhook or Slack.
Instant accounts
provision_account issues an API key with no email.
Usage view
get_usage shows plan usage and limits.
No hosting
Runs locally through npx as a thin REST client.

Good for

  • Poll an endpoint every few minutes without writing a scheduler
  • Schedule a one-time call for a launch date
  • Review failed runs of a billing job
  • Pause and resume jobs during maintenance
  • Set up alerts for failing webhooks

Pricing

Freemium, from $19 a month

Free plan; paid plans $19, $59 and $129 per month

Prices change. Check runhooks.app before you buy.

Runhooks FAQ

Do I need an account first?

No. Ask the agent to run provision_account, or get a key from the dashboard or CLI.

Where does the key go?

Set RUNHOOKS_API_KEY in the client config; provision_account also saves one to ~/.runhooks/mcp.json.

What does it cost?

The MCP server adds no cost; usage counts against your plan, which starts Free and goes up to $19, $59 and $129 a month.

Can I point it elsewhere?

Yes, RUNHOOKS_API_URL overrides the API origin.

Is Runhooks free?

Runhooks has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

How do I add Runhooks to Claude Code?

Run this command in your terminal: claude mcp add runhooks-mcp --env RUNHOOKS_API_KEY='<RUNHOOKS_API_KEY>' -- npx -y @runhooks/mcp

What are the best alternatives to Runhooks?

The closest alternatives to Runhooks are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Runhooks

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ha MCP

    MCP server

    MCP server for managing and automating Home Assistant from AI assistants

    Runs locally
    • 8 tools
    • Open source
    • 7.9K GitHub stars
    • Productivity