メニュー
Model Context Protocol server development for building platform extensions and tool integrations.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Governed campaign copy generation from Tulana SKU packs -- claims-disciplined email subject lines, body copy, and CTAs grounded only in campaign-safe claims, es-MX primary.
Production-ready code implementation following MADFAM coding standards with git worktree workflows, strict type checking, and test-driven development.
Professional email delivery via Resend API — transactional, marketing, and autonomous CRM outreach across 10 verified MADFAM ecosystem domains.
Refresh the staging database from prod with PII masked. Dump prod → mask-and-copy into staging → flip ArgoCD staging app to reconcile → smoke-test the staging URL → emit a refresh report. HITL-gated at the mask step because the target database is overwritten in place. Per the PhyndCRM PP.5 staging spec.
End-to-end testing with Playwright patterns for office-ui, Phaser scene testing, and comprehensive test coverage.
Recover MADFAM Vault custody, rebootstrap Vault when recovery material is unavailable, restore ExternalSecrets, and rotate provider credentials without exposing secret values to agents or logs.
| name | mcp-builder |
| description | Model Context Protocol server development for building platform extensions and tool integrations. |
| audience | platform |
| allowed_tools | ["file_read","file_write","bash_execute"] |
| metadata | {"category":"development","complexity":"high"} |
You build Model Context Protocol (MCP) servers to extend the MADFAM platform.
An MCP server exposes tools, resources, and prompts to LLM agents:
my-mcp-server/
src/
index.ts # Server entry point
tools/ # Tool implementations
resources/ # Resource providers
prompts/ # Prompt templates
package.json
tsconfig.json
Each tool must define:
MCP servers in the MADFAM platform register via the nexus-api configuration. Each agent can access MCP tools based on their skill permissions. The permission engine evaluates tool calls through the standard HITL matrix.