{
  "markdown": "<p align=\"center\">\n  <img src=\"https://img.shields.io/badge/claude--code-plugin-8A2BE2\" alt=\"Claude Code Plugin\" />\n  <img src=\"https://img.shields.io/badge/skills-4-blue\" alt=\"4 Skills\" />\n  <img src=\"https://img.shields.io/badge/agents-2-green\" alt=\"2 Agents\" />\n  <img src=\"https://img.shields.io/badge/license-MIT-green\" alt=\"MIT License\" />\n</p>\n\n# Memoriant MCP Data Skill\n\nA Claude Code plugin for conversational data access via the Model Context Protocol (MCP). Ask questions in plain English and get answers from CRM, ticket systems, and databases — all at once, without logging into each system separately.\n\n**No servers. No Docker. Just install and use.**\n\n## Install\n\n```bash\n/install NathanMaine/memoriant-mcp-data-skill\n```\n\n## Cross-Platform Support\n\n### Claude Code (Primary)\n```bash\n/install NathanMaine/memoriant-mcp-data-skill\n```\n\n### OpenAI Codex CLI\n```bash\ngit clone https://github.com/NathanMaine/memoriant-mcp-data-skill.git ~/.codex/skills/mcp-data\ncodex --enable skills\n```\n\n### Gemini CLI\n```bash\ngemini extensions install https://github.com/NathanMaine/memoriant-mcp-data-skill.git --consent\n```\n\n## Skills\n\n| Skill | Command | What It Does |\n|-------|---------|-------------|\n| **Query Data** | `/query-data` | Natural language → parallel MCP queries → unified answer |\n| **Discover Schema** | `/discover-schema` | Map all connected data sources: fields, types, relationships |\n| **Explore CRM** | `/explore-crm` | Lookup, list, filter, and summarize CRM accounts and contacts |\n| **Query Tickets** | `/query-tickets` | List, filter, count, and summarize support tickets |\n\n## Agents\n\n| Agent | Best Model | Specialty |\n|-------|-----------|-----------|\n| **Data Query Agent** | Sonnet 4.6 | Multi-source NL query, parallel tool calls, answer synthesis |\n| **Schema Explorer** | Sonnet 4.6 | Schema discovery, relationship detection, data map generation |\n\n## Quick Start\n\n```bash\n# Discover what data sources you have\n/discover-schema\n\n# Ask a plain-English question across all sources\n/query-data\n\n# Look up a specific customer\n/explore-crm\n\n# List open high-priority tickets\n/query-tickets\n```\n\n## The Core Value\n\nInstead of logging into 5 different systems to answer one customer question, ask this plugin one question:\n\n```\n\"What is the current status, open tickets, and recent orders for Acme Corp?\"\n```\n\n**Result:**\n```\nAcme Corp (CRM: Active, $45,000/year, Rep: Jane Smith)\n\nOpen Tickets (2):\n  #9871  High  \"API integration failing\"   3 days\n  #9799  Med   \"Export missing columns\"   21 days\n\nRecent Orders:\n  Order #10234  $12,500  2026-03-15  Delivered\n  Order #10198   $8,200  2026-02-28  Delivered\n\nSources: CRM (1 record), Tickets (2 open), Legacy DB (2 orders) — 0.8s\n```\n\n## MCP Tool Pattern\n\nThis plugin follows the MCP (Model Context Protocol) server pattern:\n\n```\nUser question\n  ↓\nNatural language parsing (subject, verb, object, filters)\n  ↓\nTool routing (crm / tickets / legacy_db / all)\n  ↓\nParallel MCP tool calls\n  ↓\nResponse synthesis\n  ↓\nUnified plain-language answer\n```\n\n## Connected Data Sources\n\n| Tool | Data | Example Questions |\n|------|------|-------------------|\n| `crm` | Accounts, contacts, reps, contracts | \"Who is Acme Corp's account rep?\" |\n| `tickets` | Support tickets, status, priority | \"List all critical open tickets\" |\n| `legacy_db` | Orders, transactions, products | \"Show Q1 orders over $10,000\" |\n\n## Schema Discovery\n\n```\n/discover-schema\n```\n\nOutputs `mcp-schema.md` with:\n- All available tools and their field types\n- Detected cross-source relationships (e.g., `crm.name ↔ tickets.customer`)\n- Example queries for each data source\n- Sample records to validate connectivity\n\n## Use Cases\n\n- Support team: complete customer picture before a call\n- Sales: account status + recent tickets + order history in one view\n- Operations: cross-system reporting without manual data assembly\n- Engineering: natural language database exploration during development\n- Management: aggregate counts and summaries across all systems\n\n## Using the Actual Tool\n\nThe full source code from [NathanMaine/mcp-conversational-data-agent](https://github.com/NathanMaine/mcp-conversational-data-agent) is bundled in `src/`. It implements an MCP server with three data tools: `crm`, `tickets`, and `legacy_db`.\n\n### Install\n\n```bash\n# Requires Python 3.8+\ncd src\npip install -r requirements.txt\n```\n\n### Run the MCP Server\n\n```bash\npython src/server.py\n```\n\nThe server exposes three MCP tools over stdio:\n\n| Tool | Description |\n|------|-------------|\n| `crm` | Query CRM accounts, contacts, reps, and contracts |\n| `tickets` | Query and filter support tickets by status, priority, customer |\n| `legacy_db` | Query orders, transactions, and product data |\n\n### Connect to Claude Code\n\nAdd the server to your Claude Code MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"conversational-data\": {\n      \"command\": \"python\",\n      \"args\": [\"/path/to/src/src/server.py\"]\n    }\n  }\n}\n```\n\n### Configuration\n\nEdit the tool files in `src/src/tools/` to point at your actual data sources:\n\n- `crm.py` — connect to your CRM (Salesforce, HubSpot, CSV, etc.)\n- `tickets.py` — connect to your ticketing system (Jira, Zendesk, etc.)\n- `legacy_db.py` — connect to your database (Postgres, SQLite, etc.)\n\nThe tool implementations are intentionally simple stubs — replace the return values with real queries to your systems.\n\n### Full Documentation\n\nSee the [mcp-conversational-data-agent repo](https://github.com/NathanMaine/mcp-conversational-data-agent) for the full architecture guide and examples.\n\n## Source Repository\n\nBuilt from [NathanMaine/mcp-conversational-data-agent](https://github.com/NathanMaine/mcp-conversational-data-agent).\n\n## License\n\nMIT — see [LICENSE](LICENSE) for details.\n",
  "bytes": 5734,
  "sha": "4f2e7580dff5c2d753a49244b6ce7c5e196a777be23fc1413337293ff09a4b6a",
  "repo_slug": "nathanmaine/memoriant-mcp-data-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_nathanmaine_memoriant_mcp_data_skill_mem_5799d5c4/readme"
}