watchgoose-mcp
This server lets you inspect Watchgoose cron/recurring-task monitoring through read-only MCP tools.
List checks in the project, optionally filtered by exact slug or required tags, with a limit up to 100.
Get a single check by its stable 40-character
unique_key, including current state and schedule details.List a check’s retained status changes/flips newest first, filtered by start/end Unix timestamps or lookback seconds, up to 200.
Per the README, write/admin tools exist only when explicitly enabled with a read-write key, but the provided schema contains only read-only tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@watchgoose-mcp show me the status of all my cron job checks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Watchgoose MCP
Watchgoose MCP connects MCP-capable AI clients to the Watchgoose Management API. It lets you inspect cron and recurring-task monitoring, with check changes available only when you explicitly enable writes.
Hosted connector
Use the hosted Streamable HTTP endpoint in clients that support OAuth 2.1 and Dynamic Client Registration:
https://mcp.watchgoose.com/mcpAvailable in
Watchgoose is available in the Claude connector directory.
Watchgoose is listed in ChatGPT plugins for GPT and Codex.
Watchgoose is listed in the official MCP Registry.
The watchgoose-mcp package is available on npm.
In Claude, open Settings > Connectors and add the endpoint as a custom connector. For Claude Code, run:
claude mcp add --transport http --scope user watchgoose https://mcp.watchgoose.com/mcpThe browser consent flow limits each connection to one project and defaults to read-only access. See the Watchgoose MCP documentation for the tool and privacy boundaries.
Related MCP server: uptimepage
Requirements
Node.js 20 or later
A project-scoped Watchgoose API key from Project settings → API Access → Create (read-only)
Use an hcr_ read-only key when you only need check state and status history. Use an hcw_
read-write key when you also need pings, integrations, or check changes.
Claude Desktop
Add this entry to claude_desktop_config.json and restart Claude Desktop:
{
"mcpServers": {
"watchgoose": {
"command": "npx",
"args": ["-y", "watchgoose-mcp"],
"env": {
"WATCHGOOSE_API_KEY": "hcr_your_project_key"
}
}
}
}Claude Code
claude mcp add --env WATCHGOOSE_API_KEY=hcr_your_project_key \
--transport stdio --scope user watchgoose -- npx -y watchgoose-mcpRun claude mcp get watchgoose to check the connection.
Cursor
Create .cursor/mcp.json in your project, or add the same entry to your user MCP configuration:
{
"mcpServers": {
"watchgoose": {
"command": "npx",
"args": ["-y", "watchgoose-mcp"],
"env": {
"WATCHGOOSE_API_KEY": "hcr_your_project_key"
}
}
}
}VS Code
Create .vscode/mcp.json:
{
"servers": {
"watchgoose": {
"type": "stdio",
"command": "npx",
"args": ["-y", "watchgoose-mcp"],
"env": {
"WATCHGOOSE_API_KEY": "hcr_your_project_key"
}
}
}
}Run MCP: List Servers and start watchgoose.
Cline
Cline connects to the hosted endpoint with OAuth, so no API key is needed. Open MCP Servers >
Configure MCP Servers and add this entry to cline_mcp_settings.json:
{
"mcpServers": {
"watchgoose": {
"type": "streamableHttp",
"url": "https://mcp.watchgoose.com/mcp"
}
}
}Keep "type": "streamableHttp" exactly as written; without it Cline falls back to SSE and the
connection fails. When Cline prompts you to authenticate, sign in to Watchgoose in the browser,
choose one project and keep read-only access unless you want Cline to change checks. To use a
project API key instead, add the npx entry from the Cursor section above to the same file.
Environment
Variable | Required | Default | Description |
| Yes | - | Project-scoped |
| No |
| Management API base URL. HTTPS is required except for loopback development hosts. The key is sent to this host, so use only a URL you trust. |
| No |
| Set to |
| Legacy keys only | - | Required as |
The server classifies key prefixes locally and never probes the API to infer access. Setting
WATCHGOOSE_ENABLE_WRITES=true cannot give a read-only key additional access.
Tools
Checks are addressed by stable 40-character unique_key values. UUIDs, ping URLs, and integration
UUIDs are used only inside the server and are not shown to the AI client.
Tool | Required access | Management API mapping |
| Read-only |
|
| Read-only |
|
| Read-only |
|
| Read-write | Resolve |
| Read-write |
|
| Read-write plus writes enabled |
|
| Read-write plus writes enabled | Resolve |
| Read-write plus writes enabled | Resolve |
| Read-write plus writes enabled | Resolve |
| Read-write plus writes enabled | Resolve |
Integration assignments use exact integration names. Names must be non-empty and unique within the project.
create_check is a create-or-update operation when unique is supplied: a matching existing check
has its supplied settings replaced. timeout without schedule also switches a scheduled check to
interval monitoring: the stored schedule string remains, but no longer governs cadence. Include the
confirmed schedule to retain scheduled monitoring. Other omitted settings remain unchanged.
channels: [] clears all alert integration assignments. The tool therefore advertises
destructiveHint: true. A new check awaits success/failure for completion-based cadence; a first
failure can move it down. An optional start ping can initiate runtime monitoring before completion.
List results are capped at 100 checks, 100 pings, 200 flips, and 100 integrations. Every serialized tool result is also capped at 24,000 characters. Results include metadata when entries are omitted.
Security
Writes are disabled by default, even with an
hcw_key.The API key is sent only in the
X-Api-Keyheader and is never logged or returned.API redirects are rejected so credentials cannot be forwarded to another host.
Check UUIDs, ping and update URLs, integration UUIDs, and unknown future API fields are removed from output.
Pings keep only
type,date,n,scheme,method, andduration. Source IP addresses, user agents, run IDs, and body URLs are removed.Ping bodies are never requested.
The server has no telemetry.
Protect client configuration files that contain API keys. Prefer a dedicated project and the least-privileged key that exposes the tools you need. Revoke a key from Watchgoose project settings when it is no longer in use.
Report vulnerabilities privately as described in SECURITY.md.
Workflow skills
The repository includes portable skills for auditing scheduled-job coverage, drafting single-job setup, triaging missed heartbeats, reviewing existing monitoring health, and proposing approved create-only batches from an audit, list or CSV. See the skills guide for local installation, examples, and safety boundaries. Skills do not grant additional access, automatically run jobs, or change the existing directory listings.
The installable
monitoring plugin
lives in plugins/watchgoose-monitoring/, with one canonical skill tree and remote-MCP adapters.
Load that subfolder rather than the repository root; the old root plugin/skill paths are superseded
without automatic migration of installed copies. The npm CLI and hosted endpoint remain unchanged.
Each release also publishes the plugin as the root of pixeware/watchgoose-plugin:
Gemini CLI:
gemini extensions install https://github.com/pixeware/watchgoose-pluginGrok Build:
grok plugin install pixeware/watchgoose-plugin --trustAny agent that reads Agent Skills:
npx skills add pixeware/watchgoose-plugin, then add the hosted endpoint in your client
Development
npm install
npm run format:check
npm run lint
npm run typecheck
npm test
npm run publish:dry-runProduction integration tests are opt-in and require dedicated test-project keys. They never run in CI.
Every user-visible distribution shares one release version: the npm package, server.json, the
hosted server, the Claude and portable plugin manifests and the OpenAI plugin. Bump
WATCHGOOSE_RELEASE_VERSION in packages/core/src/constants.ts and the matching manifests
together; tests/skills/release-version.test.ts fails if any of them disagree. The OpenAI upload
ZIP is built with npm run build:openai-plugin.
Support
Support: support@watchgoose.com
Documentation: watchgoose.com/docs/mcp
Privacy policy: watchgoose.com/legal/privacy
Terms of service: watchgoose.com/legal/terms
License
MIT
Various badges
Available Tools
3 toolsget_checkGet a Watchgoose checkARead-onlyIdempotentInspect
Get one check by its stable unique_key, including its current state and schedule. Cron and OnCalendar checks use schedule plus grace; simple checks use timeout plus grace.
Inputs: unique_key (required). Returns: meta, check
list_checksList Watchgoose checksARead-onlyIdempotentInspect
List checks in this Watchgoose project, optionally filtered by slug or tags. A successful ping arms a new check; Watchgoose then expects the next success within its timeout or schedule plus grace period.
Inputs: slug, tags, limit. Returns: meta, checks
list_flipsList a check's status changesARead-onlyIdempotentInspect
List retained status changes for a check, newest first, with optional time filters. In results, up: 1 means the check became up; up: 0 means any other status, including down, paused, and new after resume. A pause or resume that changes the check's status records a flip.
Inputs: unique_key (required), end, limit, start, +1 more. Returns: meta, flips
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools are clearly distinct: list checks, get a single check by key, and list status changes. There is no meaningful overlap or ambiguity between them.
All tool names follow a consistent lowercase verb_noun pattern: list_checks, get_check, list_flips. The singular/plural difference is natural and appropriate.
Three tools is well-scoped for a read-only monitoring server. Each tool provides a distinct capability with no redundancy or filler.
The read-only monitoring surface is coherent: discover checks, inspect a check, and view its flip history. Check management and ping actions appear to happen outside MCP, so the lack of mutation tools is a minor gap rather than a fatal one.
Maintenance
Related MCP Connectors
MCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents.
Manage uptime monitors, incidents and status pages from any MCP client.
Pingstack monitors cron jobs and scheduled tasks with heartbeat checks, and checks websites, TCP ports, DNS records, SSL certificates and domain expiry. This MCP server lets your agent create, update, pause and delete checks, build dashboards and publish them as status pages, manage notification groups, and read incidents with their causes, uptime, run history and latency. Pause, delete and unpublish stay off until you turn them on. Browser sign-in, no API key needed.
Uptime, SSL, DNS and domain monitoring you can talk to from Claude or any MCP client.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for CronAlert uptime monitoring — manage monitors, check results, and incidents from any MCP-compatible AI client.9102 npmMIT

uptimepageofficial
AlicenseNot gradedqualityBmaintenanceMCP server for Uptimepage uptime monitoring. An LLM client can read your monitors and incidents, run a check on demand, and post incident updates. Writes need an OAuth login and a scoped token, and each one is logged.60AGPL 3.0- AlicenseAqualityAmaintenanceUptime monitoring from your AI agent: create and diagnose checks (40 types: HTTP, TCP, DNS, SSL, ICMP, databases, message queues and more), read results and incidents, and manage status pages and maintenance windows. Built into the self-hostable SolidPing server, served over streamable HTTP at /api/v1/mcp.2342AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients such as Claude to check current uptime status, inspect monitors and incidents, trigger fresh checks, and retrieve status summaries from a self-hosted monitoring service.2MIT