Model Context Protocol server for Runhooks — let AI agents schedule and manage HTTP webhooks
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
RUNHOOKS_API_KEYAPI keyoptionalRunhooks API key (rh_live_...). Required for all tools except provision_account; get one instantly with the provision_account tool, the dashboard, or the CLI.
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
provision_accountCreate a new anonymous Runhooks account (no email required) and return an API key. Save the returned apiKey and set it as RUNHOOKS_API_KEY to use every other tool.Create a new anonymous Runhooks account (no email required) and return an API key. Save the returned apiKey and set it as RUNHOOKS_API_KEY to use every other tool.
No input schema was published for this tool.
whoamiShow the currently authenticated Runhooks account (name, plan, API key prefix).Show the currently authenticated Runhooks account (name, plan, API key prefix).
No input schema was published for this tool.
rotate_keyRotate the API key. The old key stops working immediately; the new key is returned.Rotate the API key. The old key stops working immediately; the new key is returned.
No input schema was published for this tool.
create_jobNo description publishedThis tool published no description. Forge does not invent one.
list_jobsList your scheduled jobs with optional filters and pagination.List your scheduled jobs with optional filters and pagination.
No input schema was published for this tool.
get_jobGet a single job by its ID.Get a single job by its ID.
No input schema was published for this tool.
update_jobUpdate an existing job. Only the fields you provide are changed.Update an existing job. Only the fields you provide are changed.
No input schema was published for this tool.
delete_jobprivilegedDelete a job permanently.Delete a job permanently.
No input schema was published for this tool.
pause_jobPause a job — it stops executing until resumed.Pause a job — it stops executing until resumed.
No input schema was published for this tool.
resume_jobResume a paused job.Resume a paused job.
No input schema was published for this tool.
list_executionsList recent executions (run history) for a job.List recent executions (run history) for a job.
No input schema was published for this tool.
replay_executionRe-run a past execution immediately.Re-run a past execution immediately.
No input schema was published for this tool.
get_usageShow the current plan usage and limits for the account.Show the current plan usage and limits for the account.
No input schema was published for this tool.
list_alertsList your failure-alert configurations.List your failure-alert configurations.
No input schema was published for this tool.
create_alertCreate a failure alert. Fires when a job dead-letters. Channel is email, webhook, or slack.Create a failure alert. Fires when a job dead-letters. Channel is email, webhook, or slack.
No input schema was published for this tool.
get_alertGet a single alert configuration by its ID.Get a single alert configuration by its ID.
No input schema was published for this tool.
update_alertUpdate an alert configuration. Only the fields you provide are changed.Update an alert configuration. Only the fields you provide are changed.
No input schema was published for this tool.
delete_alertprivilegedDelete an alert configuration.Delete an alert configuration.
No input schema was published for this tool.
17 of 18 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Model Context Protocol server for Runhooks — let AI agents schedule and manage HTTP webhooks
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
55 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+43 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.