@cubis/foundry 0.3.31 → 0.3.33

package/mcp/README.md

@@ -0,0 +1,17 @@
+# MCP Skill Catalog
+
+This directory contains MCP-focused skills and powers separated from workflow-first skills.
+
+## Layout
+
+- `mcp/skills/<skill-id>/...`: canonical MCP skills
+- `mcp/powers/<skill-id>/...`: canonical MCP powers
+- `mcp/catalogs/default.json`: default MCP profile used by `--include-mcp`
+
+## Install Behavior
+
+- `cbx workflows install` defaults to workflow profile `core` (no MCP skills).
+- Add `--include-mcp` to append MCP skills from `mcp/catalogs/default.json`.
+- Use `--all-skills` to install workflow full profile + MCP skills.
+
+Legacy wrappers remain in `workflows/skills/*` and `workflows/powers/*` for compatibility.

package/mcp/catalogs/default.json

@@ -0,0 +1,14 @@
+{
+  "profile": "mcp-default",
+  "version": 1,
+  "skills": [
+    "postman",
+    "atlassian-mcp",
+    "github-automation",
+    "sentry-automation",
+    "datadog-automation",
+    "mcp-builder",
+    "mcp-developer",
+    "building-mcp-server-on-cloudflare"
+  ]
+}

package/mcp/powers/atlassian-mcp/POWER.md

@@ -0,0 +1,91 @@
+````markdown
+---
+inclusion: manual
+name: atlassian-mcp
+description: Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
+license: MIT
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.0.0"
+  domain: platform
+  triggers: Jira, Confluence, Atlassian, MCP, tickets, issues, wiki, JQL, CQL, sprint, backlog, project management
+  role: expert
+  scope: implementation
+  output-format: code
+  related-skills: mcp-developer, api-designer, security-reviewer
+---
+
+# Atlassian MCP Expert
+
+Senior integration specialist with deep expertise in connecting Jira, Confluence, and other Atlassian tools to AI systems via Model Context Protocol (MCP).
+
+## Role Definition
+
+You are an expert in Atlassian MCP integration with mastery of both official and open-source MCP servers, JQL/CQL query languages, OAuth 2.0 authentication, and production deployment patterns. You build robust workflows that automate issue triage, documentation sync, sprint planning, and cross-tool integration while respecting permissions and maintaining security.
+
+## When to Use This Skill
+
+- Querying Jira issues with JQL filters
+- Searching or creating Confluence pages
+- Automating sprint workflows and backlog management
+- Setting up MCP server authentication (OAuth/API tokens)
+- Syncing meeting notes to Jira tickets
+- Generating documentation from issue data
+- Debugging Atlassian API integration issues
+- Choosing between official vs open-source MCP servers
+
+## Core Workflow
+
+1. **Select server** - Choose official cloud, open-source, or self-hosted MCP server
+2. **Authenticate** - Configure OAuth 2.1, API tokens, or PAT credentials
+3. **Design queries** - Write JQL for Jira, CQL for Confluence, test filters
+4. **Implement workflow** - Build tool calls, handle pagination, error recovery
+5. **Deploy** - Configure IDE integration, test permissions, monitor rate limits
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| Server Setup | `references/mcp-server-setup.md` | Installation, choosing servers, configuration |
+| Jira Operations | `references/jira-queries.md` | JQL syntax, issue CRUD, sprints, boards |
+| Confluence Ops | `references/confluence-operations.md` | CQL search, page creation, spaces, comments |
+| Authentication | `references/authentication-patterns.md` | OAuth 2.0, API tokens, permission scopes |
+| Common Workflows | `references/common-workflows.md` | Issue triage, doc sync, sprint automation |
+
+## Constraints
+
+### MUST DO
+- Respect user permissions and workspace access controls
+- Validate JQL/CQL queries before execution
+- Handle rate limits with exponential backoff
+- Use pagination for large result sets (50-100 items per page)
+- Implement error recovery for network failures
+- Log API calls for debugging and audit trails
+- Test with read-only operations first
+- Document required permission scopes
+
+### MUST NOT DO
+- Hardcode API tokens or OAuth secrets in code
+- Ignore rate limit headers from Atlassian APIs
+- Create issues without validating required fields
+- Skip input sanitization on user-provided query strings
+- Deploy without testing permission boundaries
+- Update production data without confirmation prompts
+- Mix different authentication methods in same session
+- Expose sensitive issue data in logs or error messages
+
+## Output Templates
+
+When implementing Atlassian MCP features, provide:
+1. MCP server configuration (JSON/environment vars)
+2. Query examples (JQL/CQL with explanations)
+3. Tool call implementation with error handling
+4. Authentication setup instructions
+5. Brief explanation of permission requirements
+
+## Knowledge Reference
+
+Atlassian MCP Server (official), mcp-atlassian (sooperset), atlassian-mcp (xuanxt), JQL (Jira Query Language), CQL (Confluence Query Language), OAuth 2.1, API tokens, Personal Access Tokens (PAT), Model Context Protocol, JSON-RPC 2.0, rate limiting, pagination, permission scopes, Jira REST API, Confluence REST API
+````

package/mcp/powers/atlassian-mcp/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: atlassian-mcp
+description: Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
+license: MIT
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.0.0"
+  domain: platform
+  triggers: Jira, Confluence, Atlassian, MCP, tickets, issues, wiki, JQL, CQL, sprint, backlog, project management
+  role: expert
+  scope: implementation
+  output-format: code
+  related-skills: mcp-developer, api-designer, security-reviewer
+---
+
+# Atlassian MCP Expert
+
+Senior integration specialist with deep expertise in connecting Jira, Confluence, and other Atlassian tools to AI systems via Model Context Protocol (MCP).
+
+## Role Definition
+
+You are an expert in Atlassian MCP integration with mastery of both official and open-source MCP servers, JQL/CQL query languages, OAuth 2.0 authentication, and production deployment patterns. You build robust workflows that automate issue triage, documentation sync, sprint planning, and cross-tool integration while respecting permissions and maintaining security.
+
+## When to Use This Skill
+
+- Querying Jira issues with JQL filters
+- Searching or creating Confluence pages
+- Automating sprint workflows and backlog management
+- Setting up MCP server authentication (OAuth/API tokens)
+- Syncing meeting notes to Jira tickets
+- Generating documentation from issue data
+- Debugging Atlassian API integration issues
+- Choosing between official vs open-source MCP servers
+
+## Core Workflow
+
+1. **Select server** - Choose official cloud, open-source, or self-hosted MCP server
+2. **Authenticate** - Configure OAuth 2.1, API tokens, or PAT credentials
+3. **Design queries** - Write JQL for Jira, CQL for Confluence, test filters
+4. **Implement workflow** - Build tool calls, handle pagination, error recovery
+5. **Deploy** - Configure IDE integration, test permissions, monitor rate limits
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| Server Setup | `references/mcp-server-setup.md` | Installation, choosing servers, configuration |
+| Jira Operations | `references/jira-queries.md` | JQL syntax, issue CRUD, sprints, boards |
+| Confluence Ops | `references/confluence-operations.md` | CQL search, page creation, spaces, comments |
+| Authentication | `references/authentication-patterns.md` | OAuth 2.0, API tokens, permission scopes |
+| Common Workflows | `references/common-workflows.md` | Issue triage, doc sync, sprint automation |
+
+## Constraints
+
+### MUST DO
+- Respect user permissions and workspace access controls
+- Validate JQL/CQL queries before execution
+- Handle rate limits with exponential backoff
+- Use pagination for large result sets (50-100 items per page)
+- Implement error recovery for network failures
+- Log API calls for debugging and audit trails
+- Test with read-only operations first
+- Document required permission scopes
+
+### MUST NOT DO
+- Hardcode API tokens or OAuth secrets in code
+- Ignore rate limit headers from Atlassian APIs
+- Create issues without validating required fields
+- Skip input sanitization on user-provided query strings
+- Deploy without testing permission boundaries
+- Update production data without confirmation prompts
+- Mix different authentication methods in same session
+- Expose sensitive issue data in logs or error messages
+
+## Output Templates
+
+When implementing Atlassian MCP features, provide:
+1. MCP server configuration (JSON/environment vars)
+2. Query examples (JQL/CQL with explanations)
+3. Tool call implementation with error handling
+4. Authentication setup instructions
+5. Brief explanation of permission requirements
+
+## Knowledge Reference
+
+Atlassian MCP Server (official), mcp-atlassian (sooperset), atlassian-mcp (xuanxt), JQL (Jira Query Language), CQL (Confluence Query Language), OAuth 2.1, API tokens, Personal Access Tokens (PAT), Model Context Protocol, JSON-RPC 2.0, rate limiting, pagination, permission scopes, Jira REST API, Confluence REST API

package/mcp/powers/building-mcp-server-on-cloudflare/POWER.md

@@ -0,0 +1,261 @@
+````markdown
+---
+inclusion: manual
+name: building-mcp-server-on-cloudflare
+description: Build and deploy remote MCP servers on Cloudflare Workers with tools, OAuth authentication, and production configuration.
+---
+
+# Building MCP Servers on Cloudflare
+
+Creates production-ready Model Context Protocol servers on Cloudflare Workers with tools, authentication, and deployment.
+
+## When to Use
+
+- User wants to build a remote MCP server
+- User needs to expose tools via MCP
+- User asks about MCP authentication or OAuth
+- User wants to deploy MCP to Cloudflare Workers
+
+## Prerequisites
+
+- Cloudflare account with Workers enabled
+- Node.js 18+ and npm/pnpm/yarn
+- Wrangler CLI (`npm install -g wrangler`)
+
+## Quick Start
+
+### Option 1: Public Server (No Auth)
+
+```bash
+npm create cloudflare@latest -- my-mcp-server \
+  --template=cloudflare/ai/demos/remote-mcp-authless
+cd my-mcp-server
+npm start
+```
+
+Server runs at `http://localhost:8788/mcp`
+
+### Option 2: Authenticated Server (OAuth)
+
+```bash
+npm create cloudflare@latest -- my-mcp-server \
+  --template=cloudflare/ai/demos/remote-mcp-github-oauth
+cd my-mcp-server
+```
+
+Requires OAuth app setup. See [references/oauth-setup.md](references/oauth-setup.md).
+
+## Core Workflow
+
+### Step 1: Define Tools
+
+Tools are functions MCP clients can call. Define them using `server.tool()`:
+
+```typescript
+import { McpAgent } from "agents/mcp";
+import { z } from "zod";
+
+export class MyMCP extends McpAgent {
+  server = new Server({ name: "my-mcp", version: "1.0.0" });
+
+  async init() {
+    // Simple tool with parameters
+    this.server.tool(
+      "add",
+      { a: z.number(), b: z.number() },
+      async ({ a, b }) => ({
+        content: [{ type: "text", text: String(a + b) }],
+      })
+    );
+
+    // Tool that calls external API
+    this.server.tool(
+      "get_weather",
+      { city: z.string() },
+      async ({ city }) => {
+        const response = await fetch(`https://api.weather.com/${city}`);
+        const data = await response.json();
+        return {
+          content: [{ type: "text", text: JSON.stringify(data) }],
+        };
+      }
+    );
+  }
+}
+```
+
+### Step 2: Configure Entry Point
+
+**Public server** (`src/index.ts`):
+
+```typescript
+import { MyMCP } from "./mcp";
+
+export default {
+  fetch(request: Request, env: Env, ctx: ExecutionContext) {
+    const url = new URL(request.url);
+    if (url.pathname === "/mcp") {
+      return MyMCP.serveSSE("/mcp").fetch(request, env, ctx);
+    }
+    return new Response("MCP Server", { status: 200 });
+  },
+};
+
+export { MyMCP };
+```
+
+**Authenticated server** — See [references/oauth-setup.md](references/oauth-setup.md).
+
+### Step 3: Test Locally
+
+```bash
+# Start server
+npm start
+
+# In another terminal, test with MCP Inspector
+npx @modelcontextprotocol/inspector@latest
+# Open http://localhost:5173, enter http://localhost:8788/mcp
+```
+
+### Step 4: Deploy
+
+```bash
+npx wrangler deploy
+```
+
+Server accessible at `https://[worker-name].[account].workers.dev/mcp`
+
+### Step 5: Connect Clients
+
+**Claude Desktop** (`claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "my-server": {
+      "command": "npx",
+      "args": ["mcp-remote", "https://my-mcp.workers.dev/mcp"]
+    }
+  }
+}
+```
+
+Restart Claude Desktop after updating config.
+
+## Tool Patterns
+
+### Return Types
+
+```typescript
+// Text response
+return { content: [{ type: "text", text: "result" }] };
+
+// Multiple content items
+return {
+  content: [
+    { type: "text", text: "Here's the data:" },
+    { type: "text", text: JSON.stringify(data, null, 2) },
+  ],
+};
+```
+
+### Input Validation with Zod
+
+```typescript
+this.server.tool(
+  "create_user",
+  {
+    email: z.string().email(),
+    name: z.string().min(1).max(100),
+    role: z.enum(["admin", "user", "guest"]),
+    age: z.number().int().min(0).optional(),
+  },
+  async (params) => {
+    // params are fully typed and validated
+  }
+);
+```
+
+### Accessing Environment/Bindings
+
+```typescript
+export class MyMCP extends McpAgent<Env> {
+  async init() {
+    this.server.tool("query_db", { sql: z.string() }, async ({ sql }) => {
+      // Access D1 binding
+      const result = await this.env.DB.prepare(sql).all();
+      return { content: [{ type: "text", text: JSON.stringify(result) }] };
+    });
+  }
+}
+```
+
+## Authentication
+
+For OAuth-protected servers, see [references/oauth-setup.md](references/oauth-setup.md).
+
+Supported providers:
+- GitHub
+- Google
+- Auth0
+- Stytch
+- WorkOS
+- Any OAuth 2.0 compliant provider
+
+## Wrangler Configuration
+
+Minimal `wrangler.toml`:
+
+```toml
+name = "my-mcp-server"
+main = "src/index.ts"
+compatibility_date = "2024-12-01"
+
+[durable_objects]
+bindings = [{ name = "MCP", class_name = "MyMCP" }]
+
+[[migrations]]
+tag = "v1"
+new_classes = ["MyMCP"]
+```
+
+With bindings (D1, KV, etc.):
+
+```toml
+[[d1_databases]]
+binding = "DB"
+database_name = "my-db"
+database_id = "xxx"
+
+[[kv_namespaces]]
+binding = "KV"
+id = "xxx"
+```
+
+## Common Issues
+
+### "Tool not found" in Client
+
+1. Verify tool name matches exactly (case-sensitive)
+2. Ensure `init()` registers tools before connections
+3. Check server logs: `wrangler tail`
+
+### Connection Fails
+
+1. Confirm endpoint path is `/mcp`
+2. Check CORS if browser-based client
+3. Verify Worker is deployed: `wrangler deployments list`
+
+### OAuth Redirect Errors
+
+1. Callback URL must match OAuth app config exactly
+2. Check `GITHUB_CLIENT_ID` and `GITHUB_CLIENT_SECRET` are set
+3. For local dev, use `http://localhost:8788/callback`
+
+## References
+
+- [references/examples.md](references/examples.md) — Official templates and production examples
+- [references/oauth-setup.md](references/oauth-setup.md) — OAuth provider configuration
+- [references/tool-patterns.md](references/tool-patterns.md) — Advanced tool examples
+- [references/troubleshooting.md](references/troubleshooting.md) — Error codes and fixes
+````