import { McpServer } from "@modelcontextprotocol/server"; import type { Paths } from "./paths.js"; export declare const MCP_INSTRUCTIONS = "skillhook turns this machine into a webhook endpoint that runs Agent Skills (SKILL.md files) with Claude Code or Codex.\nTypical flow: skillhook_status \u2192 create_skill (or add_example) \u2192 set_secret/generate_secret \u2192 run_skill to test locally \u2192 get_webhook_urls to hand the URL to the sender (Granola, Sentry, GitHub, Zapier\u2026).\nSkills live in /skills//SKILL.md; the `skillhook:` frontmatter block sets runner, model, auth and filters. Secrets live in /.env and are never returned by tools except right after generation.\nA repository can declare its own hooks in a version-controlled skillhook.yaml (webhook name \u2192 run: shell command | skill: SKILL.md directory | prompt: inline instructions); link_project registers it so the hooks are served, list_projects shows what runs from which webhook.\nA `schedule:` key (cron expression, optional timezone/catch_up/overlap) on any skill or hook makes the running server fire it on time without a webhook; `webhook: false` makes it schedule-only. list_schedules shows the next and last runs.\nJobs are directories under /jobs/ with payload.json, prompt.md, stdout.log, result.md and, when the agent reported one, response.json. A job's `status` says how the process ended; its `outcome` (completed, partial, needs_human, nothing_to_do, failed, unknown) says whether the task was done, as reported by the agent through response.json or a structured answer (`response: { mode: structured }` in the skill).\nEvery webhook the server received, including rejected, filtered and duplicate ones, is in the delivery log: list_deliveries and get_delivery show what arrived and why it did not run; replay_delivery (or replay_job) runs it again through the skill as it is now.\nWhile it runs, an agent reports progress and can ask a person a question through the job API (the job_* tools of `skillhook mcp --job`, or `skillhook job \u2026`); such jobs show `progress`, `question` and `answer`. list_jobs with waiting: true lists what waits for a person (an open question, or a finished job with outcome needs_human); answer_job delivers the answer to the waiting agent, or starts a new job (trigger `resume`) that continues the agent's session with it.\nget_health, get_runners and get_stats answer whether the CLIs, their MCP servers and the skills are healthy and how the jobs went; get_config / update_config / restart_server change the running server. cloud_status tells whether the machine is paired with Skillhook Cloud and whether an organisation API key is kept here; pairing itself is only done by the person in a terminal (`skillhook cloud connect --code \u2026`), never by an agent. cloud_report_issue sends a problem report to the Skillhook team from a paired machine, when the person asks for one.\nThese tools are this machine's own skillhook. The whole organisation (every machine's jobs, deliveries, alerts, health and stats, answering agents, running skills, hosted URLs: what the Skillhook Cloud dashboard shows and does) is the separate skillhook-cloud MCP server (`skillhook mcp --cloud`, part of the skillhook plugin), once signed in: its skillhook_cloud_setup tool signs in with the browser (the person approves a code there), as `skillhook cloud login` does in a terminal."; export declare function buildMcpServer(paths: Paths, env?: NodeJS.ProcessEnv): McpServer; export declare function serveMcp(paths: Paths): Promise;