@cubis/foundry 0.3.34 → 0.3.36

package/mcp/skills/building-mcp-server-on-cloudflare/references/tool-patterns.md

@@ -1,29 +0,0 @@
-# Tool Patterns for Cloudflare MCP Servers
-
-Use these patterns when defining tools in a Worker-based MCP server.
-
-## 1) Read-only lookup tool
-- Purpose: fetch status/info without side effects.
-- Input schema: strict object with required identifiers.
-- Output: typed payload + stable error shape.
-
-## 2) Mutating action tool
-- Purpose: create/update/delete with explicit confirmation rules.
-- Input schema: include idempotency key when possible.
-- Output: operation result with `changed: true|false`.
-
-## 3) Search/list tool
-- Purpose: paginated retrieval.
-- Input schema: `limit`, `cursor` (opaque token), optional filters.
-- Output: `items`, `next_cursor`, `has_more`.
-
-## 4) Long-running task launcher
-- Purpose: start async work and return tracking handle.
-- Input schema: task definition + options.
-- Output: `task_id`, `status_url` or poll key.
-
-## Guardrails
-- Validate all tool inputs before processing.
-- Return deterministic errors with machine-readable codes.
-- Avoid leaking secrets in logs or output.
-- Keep tool names stable once published.

package/mcp/skills/building-mcp-server-on-cloudflare/references/troubleshooting.md

@@ -1,317 +0,0 @@
-# MCP Server Troubleshooting
-
-Common errors and solutions for MCP servers on Cloudflare.
-
-## Connection Issues
-
-### "Failed to connect to MCP server"
-
-**Symptoms:** Client cannot establish connection to deployed server.
-
-**Causes & Solutions:**
-
-1. **Wrong URL path**
-   ```
-   # Wrong
-   https://my-server.workers.dev/
-
-   # Correct
-   https://my-server.workers.dev/mcp
-   ```
-
-2. **Worker not deployed**
-   ```bash
-   wrangler deployments list
-   # If empty, deploy first:
-   wrangler deploy
-   ```
-
-3. **Worker crashed on startup**
-   ```bash
-   wrangler tail
-   # Check for initialization errors
-   ```
-
-### "WebSocket connection failed"
-
-MCP uses SSE (Server-Sent Events), not WebSockets. Ensure your client is configured for SSE transport:
-
-```json
-{
-  "mcpServers": {
-    "my-server": {
-      "command": "npx",
-      "args": ["mcp-remote", "https://my-server.workers.dev/mcp"]
-    }
-  }
-}
-```
-
-### CORS Errors in Browser
-
-If calling from browser-based client:
-
-```typescript
-// Add CORS headers to your worker
-export default {
-  async fetch(request: Request, env: Env) {
-    // Handle preflight
-    if (request.method === "OPTIONS") {
-      return new Response(null, {
-        headers: {
-          "Access-Control-Allow-Origin": "*",
-          "Access-Control-Allow-Methods": "GET, POST, OPTIONS",
-          "Access-Control-Allow-Headers": "Content-Type",
-        },
-      });
-    }
-
-    const response = await handleRequest(request, env);
-
-    // Add CORS headers to response
-    const headers = new Headers(response.headers);
-    headers.set("Access-Control-Allow-Origin", "*");
-
-    return new Response(response.body, {
-      status: response.status,
-      headers,
-    });
-  },
-};
-```
-
-## Tool Errors
-
-### "Tool not found: [tool_name]"
-
-**Causes:**
-
-1. Tool not registered in `init()`
-2. Tool name mismatch (case-sensitive)
-3. `init()` threw an error before registering tool
-
-**Debug:**
-
-```typescript
-async init() {
-  console.log("Registering tools...");
-
-  this.server.tool("my_tool", { ... }, async () => { ... });
-
-  console.log("Tools registered:", this.server.listTools());
-}
-```
-
-Check logs: `wrangler tail`
-
-### "Invalid parameters for tool"
-
-Zod validation failed. Check parameter schema:
-
-```typescript
-// Schema expects number, client sent string
-this.server.tool(
-  "calculate",
-  { value: z.number() },  // Client must send number, not "123"
-  async ({ value }) => { ... }
-);
-
-// Fix: Coerce string to number
-this.server.tool(
-  "calculate",
-  { value: z.coerce.number() },  // "123" → 123
-  async ({ value }) => { ... }
-);
-```
-
-### Tool Timeout
-
-Workers have CPU time limits (10-30ms for free, longer for paid). For long operations:
-
-```typescript
-this.server.tool(
-  "long_operation",
-  { ... },
-  async (params) => {
-    // Break into smaller chunks
-    // Or use Queues/Durable Objects for background work
-
-    // Don't do this:
-    // await sleep(5000);  // Will timeout
-
-    return { content: [{ type: "text", text: "Queued for processing" }] };
-  }
-);
-```
-
-## Authentication Errors
-
-### "401 Unauthorized"
-
-OAuth token missing or expired.
-
-1. **Check client is handling OAuth flow**
-2. **Verify secrets are set:**
-   ```bash
-   wrangler secret list
-   # Should show GITHUB_CLIENT_ID, GITHUB_CLIENT_SECRET
-   ```
-
-3. **Check KV namespace exists:**
-   ```bash
-   wrangler kv namespace list
-   # Should show OAUTH_KV
-   ```
-
-### "Invalid redirect_uri"
-
-OAuth callback URL doesn't match app configuration.
-
-**Local development:**
-- OAuth app callback: `http://localhost:8788/callback`
-
-**Production:**
-- OAuth app callback: `https://[worker-name].[account].workers.dev/callback`
-
-Must match EXACTLY (including trailing slash or lack thereof).
-
-### "State mismatch" / CSRF Error
-
-State parameter validation failed.
-
-1. **Clear browser cookies and retry**
-2. **Check KV is storing state:**
-   ```typescript
-   // In your auth handler
-   console.log("Storing state:", state);
-   await env.OAUTH_KV.put(`state:${state}`, "1", { expirationTtl: 600 });
-   ```
-
-3. **Verify same domain for all requests**
-
-## Binding Errors
-
-### "Binding not found: [BINDING_NAME]"
-
-Binding not in `wrangler.toml` or not deployed.
-
-```toml
-# wrangler.toml
-[[d1_databases]]
-binding = "DB"           # Must match env.DB in code
-database_name = "mydb"
-database_id = "xxx-xxx"
-```
-
-After adding bindings: `wrangler deploy`
-
-### "D1_ERROR: no such table"
-
-Migrations not applied.
-
-```bash
-# Local
-wrangler d1 migrations apply DB_NAME --local
-
-# Production
-wrangler d1 migrations apply DB_NAME
-```
-
-### Durable Object Not Found
-
-```toml
-# wrangler.toml must have:
-[durable_objects]
-bindings = [{ name = "MCP", class_name = "MyMCP" }]
-
-[[migrations]]
-tag = "v1"
-new_classes = ["MyMCP"]
-```
-
-And class must be exported:
-
-```typescript
-export { MyMCP };  // Don't forget this!
-```
-
-## Deployment Errors
-
-### "Class MyMCP is not exported"
-
-```typescript
-// src/index.ts - Must export the class
-export { MyMCP } from "./mcp";
-
-// OR in same file
-export class MyMCP extends McpAgent { ... }
-```
-
-### "Migration required"
-
-New Durable Object class needs migration:
-
-```toml
-# Add to wrangler.toml
-[[migrations]]
-tag = "v2"  # Increment version
-new_classes = ["NewClassName"]
-# Or for renames:
-# renamed_classes = [{ from = "OldName", to = "NewName" }]
-```
-
-### Build Errors
-
-```bash
-# Clear cache and rebuild
-rm -rf node_modules .wrangler
-npm install
-wrangler deploy
-```
-
-## Debugging Tips
-
-### Enable Verbose Logging
-
-```typescript
-export class MyMCP extends McpAgent {
-  async init() {
-    console.log("MCP Server initializing...");
-    console.log("Environment:", Object.keys(this.env));
-
-    this.server.tool("test", {}, async () => {
-      console.log("Test tool called");
-      return { content: [{ type: "text", text: "OK" }] };
-    });
-
-    console.log("Tools registered");
-  }
-}
-```
-
-View logs:
-```bash
-wrangler tail --format pretty
-```
-
-### Test Locally First
-
-```bash
-npm start
-npx @modelcontextprotocol/inspector@latest
-```
-
-Always verify tools work locally before deploying.
-
-### Check Worker Health
-
-```bash
-# List deployments
-wrangler deployments list
-
-# View recent logs
-wrangler tail
-
-# Check worker status
-curl -I https://your-worker.workers.dev/mcp
-```

package/mcp/skills/datadog-automation/SKILL.md

@@ -1,235 +0,0 @@
----
-name: datadog-automation
-description: "Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas."
-requires:
-  mcp: [rube]
----
-
-# Datadog Automation via Rube MCP
-
-Automate Datadog monitoring and observability operations through Composio's Datadog toolkit via Rube MCP.
-
-## Prerequisites
-
-- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
-- Active Datadog connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `datadog`
-- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
-
-## Setup
-
-**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
-
-
-1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
-2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `datadog`
-3. If connection is not ACTIVE, follow the returned auth link to complete Datadog authentication
-4. Confirm connection status shows ACTIVE before running any workflows
-
-## Core Workflows
-
-### 1. Query and Explore Metrics
-
-**When to use**: User wants to query metric data or list available metrics
-
-**Tool sequence**:
-1. `DATADOG_LIST_METRICS` - List available metric names [Optional]
-2. `DATADOG_QUERY_METRICS` - Query metric time series data [Required]
-
-**Key parameters**:
-- `query`: Datadog metric query string (e.g., `avg:system.cpu.user{host:web01}`)
-- `from`: Start timestamp (Unix epoch seconds)
-- `to`: End timestamp (Unix epoch seconds)
-- `q`: Search string for listing metrics
-
-**Pitfalls**:
-- Query syntax follows Datadog's metric query format: `aggregation:metric_name{tag_filters}`
-- `from` and `to` are Unix epoch timestamps in seconds, not milliseconds
-- Valid aggregations: `avg`, `sum`, `min`, `max`, `count`
-- Tag filters use curly braces: `{host:web01,env:prod}`
-- Time range should not exceed Datadog's retention limits for the metric type
-
-### 2. Search and Analyze Logs
-
-**When to use**: User wants to search log entries or list log indexes
-
-**Tool sequence**:
-1. `DATADOG_LIST_LOG_INDEXES` - List available log indexes [Optional]
-2. `DATADOG_SEARCH_LOGS` - Search logs with query and filters [Required]
-
-**Key parameters**:
-- `query`: Log search query using Datadog log query syntax
-- `from`: Start time (ISO 8601 or Unix timestamp)
-- `to`: End time (ISO 8601 or Unix timestamp)
-- `sort`: Sort order ('asc' or 'desc')
-- `limit`: Number of log entries to return
-
-**Pitfalls**:
-- Log queries use Datadog's log search syntax: `service:web status:error`
-- Search is limited to retained logs within the configured retention period
-- Large result sets require pagination; check for cursor/page tokens
-- Log indexes control routing and retention; filter by index if known
-
-### 3. Manage Monitors
-
-**When to use**: User wants to create, update, mute, or inspect monitors
-
-**Tool sequence**:
-1. `DATADOG_LIST_MONITORS` - List all monitors with filters [Required]
-2. `DATADOG_GET_MONITOR` - Get specific monitor details [Optional]
-3. `DATADOG_CREATE_MONITOR` - Create a new monitor [Optional]
-4. `DATADOG_UPDATE_MONITOR` - Update monitor configuration [Optional]
-5. `DATADOG_MUTE_MONITOR` - Silence a monitor temporarily [Optional]
-6. `DATADOG_UNMUTE_MONITOR` - Re-enable a muted monitor [Optional]
-
-**Key parameters**:
-- `monitor_id`: Numeric monitor ID
-- `name`: Monitor display name
-- `type`: Monitor type ('metric alert', 'service check', 'log alert', 'query alert', etc.)
-- `query`: Monitor query defining the alert condition
-- `message`: Notification message with @mentions
-- `tags`: Array of tag strings
-- `thresholds`: Alert threshold values (`critical`, `warning`, `ok`)
-
-**Pitfalls**:
-- Monitor `type` must match the query type; mismatches cause creation failures
-- `message` supports @mentions for notifications (e.g., `@slack-channel`, `@pagerduty`)
-- Thresholds vary by monitor type; metric monitors need `critical` at minimum
-- Muting a monitor suppresses notifications but the monitor still evaluates
-- Monitor IDs are numeric integers
-
-### 4. Manage Dashboards
-
-**When to use**: User wants to list, view, update, or delete dashboards
-
-**Tool sequence**:
-1. `DATADOG_LIST_DASHBOARDS` - List all dashboards [Required]
-2. `DATADOG_GET_DASHBOARD` - Get full dashboard definition [Optional]
-3. `DATADOG_UPDATE_DASHBOARD` - Update dashboard layout or widgets [Optional]
-4. `DATADOG_DELETE_DASHBOARD` - Remove a dashboard (irreversible) [Optional]
-
-**Key parameters**:
-- `dashboard_id`: Dashboard identifier string
-- `title`: Dashboard title
-- `layout_type`: 'ordered' (grid) or 'free' (freeform positioning)
-- `widgets`: Array of widget definition objects
-- `description`: Dashboard description
-
-**Pitfalls**:
-- Dashboard IDs are alphanumeric strings (e.g., 'abc-def-ghi'), not numeric
-- `layout_type` cannot be changed after creation; must recreate the dashboard
-- Widget definitions are complex nested objects; get existing dashboard first to understand structure
-- DELETE is permanent; there is no undo
-
-### 5. Create Events and Manage Downtimes
-
-**When to use**: User wants to post events or schedule maintenance downtimes
-
-**Tool sequence**:
-1. `DATADOG_LIST_EVENTS` - List existing events [Optional]
-2. `DATADOG_CREATE_EVENT` - Post a new event [Required]
-3. `DATADOG_CREATE_DOWNTIME` - Schedule a maintenance downtime [Optional]
-
-**Key parameters for events**:
-- `title`: Event title
-- `text`: Event body text (supports markdown)
-- `alert_type`: Event severity ('error', 'warning', 'info', 'success')
-- `tags`: Array of tag strings
-
-**Key parameters for downtimes**:
-- `scope`: Tag scope for the downtime (e.g., `host:web01`)
-- `start`: Start time (Unix epoch)
-- `end`: End time (Unix epoch; omit for indefinite)
-- `message`: Downtime description
-- `monitor_id`: Specific monitor to downtime (optional, omit for scope-based)
-
-**Pitfalls**:
-- Event `text` supports Datadog's markdown format including @mentions
-- Downtimes scope uses tag syntax: `host:web01`, `env:staging`
-- Omitting `end` creates an indefinite downtime; always set an end time for maintenance
-- Downtime `monitor_id` narrows to a single monitor; scope applies to all matching monitors
-
-### 6. Manage Hosts and Traces
-
-**When to use**: User wants to list infrastructure hosts or inspect distributed traces
-
-**Tool sequence**:
-1. `DATADOG_LIST_HOSTS` - List all reporting hosts [Required]
-2. `DATADOG_GET_TRACE_BY_ID` - Get a specific distributed trace [Optional]
-
-**Key parameters**:
-- `filter`: Host search filter string
-- `sort_field`: Sort hosts by field (e.g., 'name', 'apps', 'cpu')
-- `sort_dir`: Sort direction ('asc' or 'desc')
-- `trace_id`: Distributed trace ID for trace lookup
-
-**Pitfalls**:
-- Host list includes all hosts reporting to Datadog within the retention window
-- Trace IDs are long numeric strings; ensure exact match
-- Hosts that stop reporting are retained for a configured period before removal
-
-## Common Patterns
-
-### Monitor Query Syntax
-
-**Metric alerts**:
-```
-avg(last_5m):avg:system.cpu.user{env:prod} > 90
-```
-
-**Log alerts**:
-```
-logs("service:web status:error").index("main").rollup("count").last("5m") > 10
-```
-
-### Tag Filtering
-
-- Tags use `key:value` format: `host:web01`, `env:prod`, `service:api`
-- Multiple tags: `{host:web01,env:prod}` (AND logic)
-- Wildcard: `host:web*`
-
-### Pagination
-
-- Use `page` and `page_size` or offset-based pagination depending on endpoint
-- Check response for total count to determine if more pages exist
-- Continue until all results are retrieved
-
-## Known Pitfalls
-
-**Timestamps**:
-- Most endpoints use Unix epoch seconds (not milliseconds)
-- Some endpoints accept ISO 8601; check tool schema
-- Time ranges should be reasonable (not years of data)
-
-**Query Syntax**:
-- Metric queries: `aggregation:metric{tags}`
-- Log queries: `field:value` pairs
-- Monitor queries vary by type; check Datadog documentation
-
-**Rate Limits**:
-- Datadog API has per-endpoint rate limits
-- Implement backoff on 429 responses
-- Batch operations where possible
-
-## Quick Reference
-
-| Task | Tool Slug | Key Params |
-|------|-----------|------------|
-| Query metrics | DATADOG_QUERY_METRICS | query, from, to |
-| List metrics | DATADOG_LIST_METRICS | q |
-| Search logs | DATADOG_SEARCH_LOGS | query, from, to, limit |
-| List log indexes | DATADOG_LIST_LOG_INDEXES | (none) |
-| List monitors | DATADOG_LIST_MONITORS | tags |
-| Get monitor | DATADOG_GET_MONITOR | monitor_id |
-| Create monitor | DATADOG_CREATE_MONITOR | name, type, query, message |
-| Update monitor | DATADOG_UPDATE_MONITOR | monitor_id |
-| Mute monitor | DATADOG_MUTE_MONITOR | monitor_id |
-| Unmute monitor | DATADOG_UNMUTE_MONITOR | monitor_id |
-| List dashboards | DATADOG_LIST_DASHBOARDS | (none) |
-| Get dashboard | DATADOG_GET_DASHBOARD | dashboard_id |
-| Update dashboard | DATADOG_UPDATE_DASHBOARD | dashboard_id, title, widgets |
-| Delete dashboard | DATADOG_DELETE_DASHBOARD | dashboard_id |
-| List events | DATADOG_LIST_EVENTS | start, end |
-| Create event | DATADOG_CREATE_EVENT | title, text, alert_type |
-| Create downtime | DATADOG_CREATE_DOWNTIME | scope, start, end |
-| List hosts | DATADOG_LIST_HOSTS | filter, sort_field |
-| Get trace | DATADOG_GET_TRACE_BY_ID | trace_id |