Quick Start

Pipelex lets you build AI methods with your coding agent and run them anywhere — from your agent or your chatbot via MCP, as a webapp, or via API in any software.

1. Sign up

Sign up at app.pipelex.com.

2. Install the Pipelex plugin in your coding agent

The plugin is how you build methods: it gives your agent the skills that write and run them, a hook that checks every edit, and the Pipelex tools. The plugin's hook and the Pipelex tools run on Node.js, so you need Node.js on your PATH.

claude plugin marketplace add Pipelex/pipelex-plugins
claude plugin install pipelex@pipelex-plugins

codex plugin marketplace add Pipelex/pipelex-plugins
export PIPELEX_API_KEY=plx_sk_...     # create one in your console at app.pipelex.com

What the plugin holds, skill by skill, is on the Pipelex Plugin page.

3. Ask your agent for the method you want

Design a method that reads an invoice PDF and returns the supplier, the total and the line items. Then run it on ~/Downloads/invoice.pdf and save it to my Pipelex account.

/pipelex-design writes the method, the hook checks it on every edit, /pipelex-inputs gets your file ready, and /pipelex-run starts it and prints a run id. Come back to that id for the status, the results or the files it produced, days later if you want. /pipelex-catalog saves the method to your account, where your chatbot can run it too.

Run your methods from your chatbot

The Pipelex MCP is a connector for your chatbot (ChatGPT, Claude): it gives it access to the Pipelex service, so it can list the methods saved in your account and run them right in the conversation. Your methods become your chatbot's tools. To build a method, use the Pipelex plugin in a coding agent such as Claude Code or Codex, as in steps 2 and 3 above.

Add the Pipelex MCP in your chatbot's settings by the address below — in Claude, that is Add custom connector — then sign in with your Pipelex account when asked. Nothing to install and no key: the Pipelex MCP runs on your signed-in session.

https://mcp.pipelex.com/mcp

Then ask your chatbot:

What methods do I have?

Run the invoice method on https://example.com/invoice.pdf

You get a run id straight away, and you can ask for its status, its results or the files it produced at any time.

Give the file as a URL the Pipelex MCP can reach. In ChatGPT you can attach it to the conversation instead and ask for a run on it; Claude has no way yet to hand the Pipelex MCP a file you attached.

The other two ways

As a webapp

Turn the method into a webapp with the method-app template:

src=$(mktemp -d)
git clone --depth 1 https://github.com/Pipelex/pipelex-method-apps.git "$src"
mkdir -p my-app && cp -R "$src/webapp-js/." my-app/
cd my-app && git init

export PIPELEX_API_KEY=plx_sk_...
make create METHOD=path/to/my_method.mthds
make dev

The app calls Pipelex from its own server code, so it needs a key of its own — create one in your console at app.pipelex.com. METHOD is a .mthds file, a directory of them, a method id from your catalog (mt_…), or a published address. The form and the result view are rendered from the method's own contract, so adding a method writes no form fields.

Via API

Use the method via API in any software through POST /v1/start — in TypeScript with @pipelex/sdk, in Python with pipelex-sdk, or with any HTTP client.

Create an API key in your console at app.pipelex.com and give it to your program as PIPELEX_API_KEY — the only thing to configure, since PIPELEX_BASE_URL already points at the hosted API.

export PIPELEX_API_KEY=plx_sk_...

curl -s https://api.pipelex.com/v1/start \
  -H "Authorization: Bearer $PIPELEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "method_ref": "github.com/Pipelex/methods/invoice_extraction@v0.1.1",
    "inputs": {"document": {"url": "https://raw.githubusercontent.com/Pipelex/pipelex-cookbook/main/assets/extract_proof_of_purchase/restaurant_invoice.pdf", "mime_type": "application/pdf"}}
  }'
# 202 → {"pipeline_run_id": "..."}

RUN_ID=...     # the pipeline_run_id the start returned
curl -s https://api.pipelex.com/v1/runs/$RUN_ID/results \
  -H "Authorization: Bearer $PIPELEX_API_KEY"

npm install @pipelex/sdk

import { PipelexApiClient } from "@pipelex/sdk";

const client = new PipelexApiClient({ apiKey: process.env.PIPELEX_API_KEY });

const result = await client.startAndWaitForResult({
  method_ref: "github.com/Pipelex/methods/invoice_extraction@v0.1.1",
  inputs: {
    document: { url: "https://raw.githubusercontent.com/Pipelex/pipelex-cookbook/main/assets/extract_proof_of_purchase/restaurant_invoice.pdf", mime_type: "application/pdf" },
  },
});

console.log(result.main_stuff);

pip install pipelex-sdk

import asyncio

from pipelex_sdk.client import PipelexAPIClient


async def main() -> None:
    async with PipelexAPIClient() as client:
        result = await client.start_and_wait(
            method_ref="github.com/Pipelex/methods/invoice_extraction@v0.1.1",
            inputs={
                "document": {
                    "url": "https://raw.githubusercontent.com/Pipelex/pipelex-cookbook/main/assets/extract_proof_of_purchase/restaurant_invoice.pdf",
                    "mime_type": "application/pdf",
                }
            },
        )
        print(result.main_stuff)


asyncio.run(main())

Next: what Pipelex is · documentation · your console · Discord

Prefer to run it yourself?

The Pipelex runtime runs your methods on your own machine, against the model providers you choose. Run It Yourself installs it, and The MTHDS Language Tutorial walks through writing a method by hand.