@cronicorn/mcp-server 1.18.3 → 1.19.1

package/dist/docs/mcp-server.md

@@ -10,49 +10,48 @@ sidebar_position: 3
 mcp:
   uri: file:///docs/mcp-server.md
   mimeType: text/markdown
-  priority: 0.9
+  priority: 0.95
+  lastModified: 2026-02-03T00:00:00Z
 ---
 
-# Chat Your Way to Scheduled Jobs
+# MCP Server
 
 [![npm version](https://badge.fury.io/js/@cronicorn%2Fmcp-server.svg)](https://www.npmjs.com/package/@cronicorn/mcp-server)
 
-**What if you could manage cron jobs by just talking to your AI assistant?**
+Manage cron jobs by talking to your AI assistant.
 
 ```
-You: "Set up a job that checks my API health every 5 minutes"
+You: "Check my API health every 5 minutes"
 
-AI: *Creates the job, adds the endpoint, configures the schedule*
-    ✅ Done! Your health check is now running every 5 minutes.
+AI: ✅ Done! Health check running every 5 minutes.
 ```
 
-**No forms. No clicking. Just conversation.**
-
 ## Quick Start
 
-### Install
-
+**Claude Code (CLI):**
 ```bash
-npm install -g @cronicorn/mcp-server
+claude mcp add cronicorn -- npx -y @cronicorn/mcp-server
 ```
 
-### Configure Your AI Assistant
-
-Add the Cronicorn MCP server to your AI assistant's configuration. The exact setup varies by tool:
-
-- **GitHub Copilot**: Add to VS Code settings
-- **Claude Desktop**: Add to `claude_desktop_config.json`
-- **Cline/Continue/Cursor**: Check your extension's MCP settings
-
-See the [full installation guide](https://github.com/weskerllc/cronicorn/tree/main/apps/mcp-server#installation) for platform-specific instructions.
+**Other assistants** (Claude Desktop, Copilot, Cursor, etc.):
+```json
+{
+  "mcpServers": {
+    "cronicorn": {
+      "command": "npx",
+      "args": ["-y", "@cronicorn/mcp-server"]
+    }
+  }
+}
+```
 
-### Authenticate
+See the [full README](https://github.com/weskerllc/cronicorn/tree/main/apps/mcp-server#setup) for platform-specific config locations.
 
-First time you use it, you'll authenticate once via OAuth (browser opens, you approve, done). The MCP server remembers you for 30 days.
+First use triggers OAuth in your browser. Approve once, stay connected for 30 days.
 
 ## What You Can Do
 
-**Create jobs instantly:**
+**Create jobs:**
 ```
 "Check https://api.myapp.com/health every 5 minutes"
 ```
@@ -62,66 +61,47 @@ First time you use it, you'll authenticate once via OAuth (browser opens, you ap
 "My payment-processor job is timing out - fix it"
 ```
 
-**Monitor everything:**
+**Monitor:**
 ```
 "Show me my dashboard stats"
-"What's wrong with that failing endpoint?"
 ```
 
-**Migrate from other systems:**
+**AI-adaptive scheduling:**
 ```
-"Help me move my 15 Vercel cron jobs to Cronicorn"
+"Monitor my API. Check more often if slow, relax when healthy."
 ```
 
-## Built-In Guides
-
-The MCP server includes interactive slash commands that guide you through common workflows:
-
-**`/setup-first-job`** - Perfect for getting started or migrating
-- Learn jobs vs endpoints, baseline schedules, AI adaptation, safety constraints
-- Get step-by-step guidance for your first scheduled task
-
-**`/troubleshoot-failures`** - Debug failing endpoints
-- Systematic diagnostic process
-- Common issues and fixes (timeouts, rate limits, auth)
-- Emergency actions when needed
+## 21 Tools Available
 
-## 30+ Tools Available
+| Category | Tools |
+|----------|-------|
+| **Jobs** | `createJob`, `listJobs`, `getJob`, `updateJob`, `archiveJob`, `pauseJob`, `resumeJob` |
+| **Endpoints** | `addEndpoint`, `listEndpoints`, `getEndpoint`, `updateEndpoint`, `archiveEndpoint`, `pauseResumeEndpoint` |
+| **AI Scheduling** | `applyIntervalHint`, `scheduleOneShot`, `clearHints`, `resetFailures` |
+| **Monitoring** | `listEndpointRuns`, `getRunDetails`, `getEndpointHealth`, `getDashboardStats` |
 
-Your AI assistant has access to tools for:
-
-- **Job Management** - Create, list, update, pause, resume, delete
-- **Endpoint Control** - Add, configure, update URLs/timeouts/schedules
-- **AI Scheduling** - Apply hints, trigger immediate runs, pause/resume
-- **Monitoring** - Health summaries, execution history, run details, dashboard stats
-
-[See all available tools →](https://github.com/weskerllc/cronicorn/tree/main/apps/mcp-server#available-tools)
+## Built-In Guides
 
-## Example Use Cases
+| Command | Description |
+|---------|-------------|
+| `/setup-first-job` | Interactive setup for your first scheduled job |
+| `/troubleshoot-failures` | Debug failing endpoints with systematic diagnosis |
 
-**Health monitoring with AI adaptation:**
-```
-"Monitor https://api.acme.com/health every minute. 
-Check more frequently if slow, relax to 5 minutes when healthy."
-```
-→ AI auto-adjusts interval based on latency in response
+## Works With
 
-**Data sync with queue monitoring:**
-```
-"Sync https://api.acme.com/sync every 5 minutes.
-Speed up when queue_depth > 100, slow down when < 10."
-```
-→ AI monitors queue_depth and adjusts schedule dynamically
+GitHub Copilot, Claude Desktop, Cursor, Cline, Continue, and any MCP-compatible assistant.
 
-**Daily cleanup:**
-```
-"Run cleanup at https://api.acme.com/cleanup daily at 2 AM Pacific"
-```
-→ Simple cron-based schedule
+## Security
 
-## Security & Compatibility
+- OAuth 2.0 Device Flow (same as AWS CLI, GitHub CLI)
+- Credentials stored locally with strict file permissions
+- Tokens auto-refresh, re-auth every 30 days
 
-**Secure authentication** via OAuth 2.0 Device Flow (same as AWS CLI, GitHub CLI). Credentials stored locally with strict permissions. Tokens refresh automatically, re-auth every 30 days.
+---
 
-**Works with** GitHub Copilot, Claude Desktop, Cline, Continue, Cursor, and any MCP-compatible AI assistant.
+## See Also
 
+- [Full README & Tool Reference](https://github.com/weskerllc/cronicorn/tree/main/apps/mcp-server)
+- [Core Concepts](./core-concepts.md) - Understanding jobs and endpoints
+- [How AI Adaptation Works](./technical/how-ai-adaptation-works.md) - AI tools and hints
+- [API Reference](./api-reference.md) - HTTP API for programmatic access

package/dist/docs/quick-start.md

@@ -9,8 +9,8 @@ sidebar_position: 3
 mcp:
   uri: file:///docs/quick-start.md
   mimeType: text/markdown
-  priority: 0.9
-  lastModified: 2025-11-02T00:00:00Z
+  priority: 0.90
+  lastModified: 2026-02-03T00:00:00Z
 ---
 
 # Quick Start Guide
@@ -217,3 +217,12 @@ If you're hitting rate limits:
 1. Increase **Min Interval** (e.g., from 30s to 60s)
 2. Adjust **Baseline Schedule** to be less frequent
 3. Let AI adapt (it will back off automatically)
+
+---
+
+## See Also
+
+- **[Core Concepts](./core-concepts.md)** - Understanding jobs, endpoints, and scheduling
+- **[API Reference](./api-reference.md)** - Programmatic access to Cronicorn
+- **[Troubleshooting](./troubleshooting.md)** - Diagnose and fix common issues
+- **[MCP Server](./mcp-server.md)** - Manage jobs via AI assistant

package/dist/docs/self-hosting.md

@@ -9,7 +9,8 @@ sidebar_position: 6
 mcp:
   uri: file:///docs/self-hosting.md
   mimeType: text/markdown
-  priority: 0.8
+  priority: 0.80
+  lastModified: 2026-02-03T00:00:00Z
 ---
 
 # Self-Hosting Guide
@@ -132,3 +133,11 @@ docker compose up -d
 - **Auth errors**: Ensure `BETTER_AUTH_SECRET` is at least 32 characters
 - **API not accessible**: Check that port 3333 isn't already in use
 - **Database issues**: Check logs with `docker compose logs db`
+
+---
+
+## See Also
+
+- **[Quick Start](./quick-start.md)** - Getting started guide
+- **[Troubleshooting](./troubleshooting.md)** - Comprehensive troubleshooting guide
+- **[API Reference](./api-reference.md)** - Programmatic access

package/dist/docs/technical/configuration-and-constraints.md

@@ -7,8 +7,8 @@ sidebar_position: 5
 mcp:
   uri: file:///docs/technical/configuration-and-constraints.md
   mimeType: text/markdown
-  priority: 0.80
-  lastModified: 2025-11-02T00:00:00Z
+  priority: 0.85
+  lastModified: 2026-02-03T00:00:00Z
 ---
 
 # Configuration and Constraints
@@ -407,3 +407,12 @@ Expensive operation runs every 10 minutes normally, AI can relax to hourly or ti
 7. **Min/max apply relative to `now`, not `lastRunAt`**
 
 Configure conservatively. The system is designed to be safe by default. Add constraints when you encounter real problems, not anticipated ones.
+
+---
+
+## See Also
+
+- **[How Scheduling Works](./how-scheduling-works.md)** - Governor logic and constraint clamping
+- **[How AI Adaptation Works](./how-ai-adaptation-works.md)** - AI tools and hints
+- **[Technical Reference](./reference.md)** - Schema and defaults
+- **[Troubleshooting](../troubleshooting.md)** - Debugging configuration issues

package/dist/docs/technical/coordinating-multiple-endpoints.md

@@ -7,8 +7,8 @@ sidebar_position: 4
 mcp:
   uri: file:///docs/technical/coordinating-multiple-endpoints.md
   mimeType: text/markdown
-  priority: 0.80
-  lastModified: 2025-11-02T00:00:00Z
+  priority: 0.75
+  lastModified: 2026-02-03T00:00:00Z
 ---
 
 # Coordinating Multiple Endpoints
@@ -449,3 +449,12 @@ When coordination isn't working:
 7. **Cross-job coordination**: Embed external status checks in responses
 
 These patterns give you the building blocks for complex workflows. Mix and match based on your needs.
+
+---
+
+## See Also
+
+- **[How AI Adaptation Works](./how-ai-adaptation-works.md)** - AI tools including sibling queries
+- **[Configuration and Constraints](./configuration-and-constraints.md)** - Endpoint configuration
+- **[Use Cases](../use-cases.md)** - Real-world examples
+- **[Technical Reference](./reference.md)** - Response body patterns