Cronicorn
Manage adaptive cron jobs and HTTP endpoint scheduling via AI assistants.
What can you do with Cronicorn?
- Adaptive scheduling — AI adjusts polling frequency based on real response data
- Plain English descriptions — no config files, no SDK required
- Safety constraints — min/max intervals and TTL-based hints that auto-expire
- Multi-endpoint coordination — endpoints are aware of siblings and adapt together
- Automatic error recovery — backoff, retry, and recovery actions out of the box
- Works without AI — traditional cron and interval scheduling as a fallback
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
@cronicorn/mcp-serverclaude mcp add cronicorn -e 'CRONICORN_API_URL=<CRONICORN_API_URL>' -e 'CRONICORN_WEB_URL=<CRONICORN_WEB_URL>' -- npx -y @cronicorn/mcp-server@1.25.0{
"mcpServers": {
"cronicorn": {
"command": "npx",
"args": [
"-y",
"@cronicorn/mcp-server@1.25.0"
],
"env": {
"CRONICORN_API_URL": "<CRONICORN_API_URL>",
"CRONICORN_WEB_URL": "<CRONICORN_WEB_URL>"
}
}
}
}Environment variables
CRONICORN_API_URLAPI base URL for CronicornCRONICORN_WEB_URLWeb UI URL for Cronicorn (used for OAuth device flow)
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Cronicorn
HTTP jobs that understand their own responses
Add endpoints, describe what matters in plain English, and the AI reads response bodies to adapt —
adjusting frequency, coordinating siblings, and recovering from failures automatically
Activity surge → AI tightens to 30s + triggers recovery actions → stabilizes → back to baseline
Features
- Adaptive scheduling — AI adjusts polling frequency based on real response data
- Plain English descriptions — no config files, no SDK required
- Safety constraints — min/max intervals and TTL-based hints that auto-expire
- Multi-endpoint coordination — endpoints are aware of siblings and adapt together
- Automatic error recovery — backoff, retry, and recovery actions out of the box
- Works without AI — traditional cron and interval scheduling as a fallback
How It Works
- Add an HTTP endpoint and set a baseline schedule (cron or interval)
- Describe what matters in plain English — thresholds, coordination logic, response structure
- AI monitors responses and adapts frequency, triggers actions, and recovers from failures automatically
Getting Started
| Path | Link |
|---|---|
| Web UI — create and manage jobs visually | cronicorn.com |
| MCP Server — manage jobs from Claude, Cursor, or any MCP client | MCP Server docs |
| API — integrate programmatically with the REST API | API Playground |
Docs · MCP Server · API · Self-Host · Support
Frequently asked questions
What is Cronicorn?
Manage adaptive cron jobs and HTTP endpoint scheduling via AI assistants.
How do I install Cronicorn?
It runs on your machine. In Claude Code: claude mcp add cronicorn -e 'CRONICORN_API_URL=<CRONICORN_API_URL>' -e 'CRONICORN_WEB_URL=<CRONICORN_WEB_URL>' -- npx -y @cronicorn/mcp-server@1.25.0. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Cronicorn need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Cronicorn open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Cronicorn?
It is published by weskerllc. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.