Flexible Orchestration
Chain any mix of processors in a single execution. Branch on LLM output, loop over lists, retry on error β all in YAML, no code required.
MCP Tool Server Β· Task Orchestration Β· LLM-Native
PETP is a pipeline execution runtime that exposes every automation as a typed MCP tool. AI agents can discover, invoke, and chain your real business operations β while processors inside each task can call LLMs themselves for intelligent decision-making.
Chain any mix of processors in a single execution. Branch on LLM output, loop over lists, retry on error β all in YAML, no code required.
Any task step can invoke an LLM processor: summarise, classify, generate, or decide. Results flow as variables into downstream steps.
Package a curated set of executions for a specific domain β procurement, finance, DevOps, HR β and expose them as a focused MCP tool-set.
Run a personal assistant on your laptop, or deploy enterprise tool-sets on Docker. Same engine, same YAML, different scale.
Download sourcing request documents, merge contracts by creation date, classify by type using LLM, then send a summary email β all triggered by a single Claude message.
Pull data from multiple spreadsheets via SSH/SFTP, merge and pivot, call an LLM to write the executive summary section, and export as a final Excel report.
Expose CI pipeline triggers, deployment scripts, log fetchers, and health-checks as MCP tools. Let Copilot or a chat agent coordinate complex release workflows.
A lightweight personal MCP tool-set on your MacBook: web scraping, local file management, calendar data extraction, and LLM-powered daily brief generation.
Define executions in YAML, start the MCP server, and any LLM agent can immediately discover and orchestrate your real-world workflows. No SDK. No boilerplate.