Skip to main content
Glama

@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.)

Related MCP server: silentwatch-mcp

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

Variable

Description

Default

RUNHOOKS_API_KEY

Your API key (rh_live_...). Optional — provision_account saves a key locally if unset. Takes precedence over the saved key.

—

RUNHOOKS_API_URL

API origin.

https://api.runhooks.app

Tools

Tool

Description

provision_account

Create an anonymous account and get an API key (no email).

whoami

Show the current account.

rotate_key

Rotate the API key.

create_job

Create a scheduled job — recurring (cron or interval) or a one-off run at a future date-time (once).

list_jobs

List jobs with filters and pagination.

get_job

Get one job by ID.

update_job

Update a job.

delete_job

Delete a job.

pause_job / resume_job

Pause or resume a job.

list_executions

List a job's run history.

replay_execution

Re-run a past execution.

get_usage

Show plan usage and limits.

list_alerts / create_alert / get_alert / update_alert / delete_alert

Manage failure alerts (email, webhook, Slack).

License

MIT

Available Tools

18 tools
create_alertB

Create a failure alert. Fires when a job dead-letters. Channel is email, webhook, or slack.

Inputs: name (required), target (required), channel (required), jobId, +3 more.

create_jobB

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.

Inputs: name (required), schedule (required), httpConfig (required), tags, +2 more.

delete_alertC

Delete an alert configuration.

Inputs: id (required).

delete_jobC

Delete a job permanently.

Inputs: id (required).

get_alertC

Get a single alert configuration by its ID.

Inputs: id (required).

get_jobC

Get a single job by its ID.

Inputs: id (required).

get_usageA

Show the current plan usage and limits for the account.

Inputs: no named parameters.

list_alertsA

List your failure-alert configurations.

Inputs: no named parameters.

list_executionsC

List recent executions (run history) for a job.

Inputs: jobId (required), page, limit, status.

list_jobsC

List your scheduled jobs with optional filters and pagination.

Inputs: tag, name, page, limit, +1 more.

pause_jobB

Pause a job — it stops executing until resumed.

Inputs: id (required).

provision_accountA

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.

Inputs: name.

replay_executionB

Re-run a past execution immediately.

Inputs: executionId (required).

resume_jobC

Resume a paused job.

Inputs: id (required).

rotate_keyA

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.

Inputs: no named parameters.

update_alertB

Update an alert configuration. Only the fields you provide are changed.

Inputs: id (required), name, jobId, target, +4 more.

update_jobC

Update an existing job. Only the fields you provide are changed.

Inputs: id (required), name, tags, status, +4 more.

whoamiA

Show the currently authenticated Runhooks account (name, plan, API key prefix).

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 18 tools

    Disambiguation5/5

    Each tool maps to a distinct resource+action: account lifecycle (provision/whoami/rotate), job CRUD plus pause/resume, execution history vs. replay, and alert CRUD. The only mild adjacency is whoami (identity/plan) vs. get_usage (limits/consumption), but their descriptions make the boundary clear. No tool pair appears to do the same thing.

    Naming Consistency4/5

    Nearly everything follows a clean snake_case verb_noun pattern (create_job, list_alerts, replay_execution, rotate_key). The single deviation is 'whoami', a conventional command-style name that breaks the pattern but remains instantly readable.

    Tool Count4/5

    18 tools across five coherent sub-domains (account, jobs, executions, usage, alerts) is reasonable, and each tool earns its place. It sits at the upper edge of comfortable scope, but the job and alert CRUD sets justify their members rather than padding the surface.

    Completeness3/5

    Jobs and alerts have full CRUD plus lifecycle controls (pause/resume), which is strong. Executions, however, only offer list and replay — there is no get_execution or log/output retrieval, so an agent that needs to diagnose why a job failed hits a dead end despite logs being referenced in create_job.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for scheduling and executing Claude Code CLI tasks via cron expressions, featuring a web dashboard and webhook support. It enables users to dynamically create custom MCP servers, manage recurring AI jobs, and track execution history with token and cost analytics.
      24
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      An MCP server that surfaces scheduled-job state and detects silent failures (exit 0 but no useful output) for cron, systemd timers, and OpenClaw schedulers, enabling AI agents to query job health and overdue status directly.
      6
      37 PyPI
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that enables AI agents to execute real-world actions through 10 specialized engines covering authenticated API calls, browser automation, visual QA, shell commands, file operations, job scraping, and parallel task execution.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that lets AI agents manage cron jobs through natural language — adding, listing, pausing, removing, running, and viewing logs of scheduled jobs with plain-English schedule parsing, automatic log capture, missed-run detection, and failure alerts.
      MIT