# Agentic Pipeline MCP

> Change or review the Python agentic_ai subsystem or Codex-facing MCP integration for this repository. Use when work touches agentic_ai/, the LangGraph pipeline, the mcp_server package, .mcp.json, or cloud adapters for the agentic pipeline.

- Skill: `hoangsonww/agentic-pipeline-mcp` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add hoangsonww/agentic-pipeline-mcp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hoangsonww/agentic-pipeline-mcp/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: hoangsonww (https://skillmd.com/u/hoangsonww)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hoangsonww/agentic-pipeline-mcp

---


# Agentic Pipeline MCP

Treat `agentic_ai/` as a separate Python project.

## Follow This Workflow

1. Read `mcp_server/app.py`, `mcp_server/tools/`, `mcp_server/resources/`, `mcp_server/prompts/`, `config/settings.py`, and `core/pipeline.py` together.
2. Use the current MCP server implementation as the source of truth for tools and resources.
3. Reconcile README claims, Make targets, and health-check assumptions before changing runtime guidance.
4. Only run local MCP or pipeline commands when the Python environment is known ready.

## Use The References

- Read `references/pipeline-map.md` for runtime paths and known drift.