Pipelex

Turn your expertise into an AI-powered App, MCP or API

Demo - Documentation - Hub - Discord

Pipelex lets you build AI methods with your coding agent and run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

1. Sign up at app.pipelex.com.

2. Install the Pipelex plugin in your coding agent. The plugin gives your agent the skills that build methods, run them and put them in your software, a hook that checks every edit, and the Pipelex tools.

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

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-run starts it and prints a run id you can come back to, and /pipelex-catalog saves it 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://raw.githubusercontent.com/Pipelex/pipelex-cookbook/main/assets/extract_proof_of_purchase/restaurant_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, built by your agent too. Ask it for a webapp around the method, and /pipelex-scaffold creates a new app from the method-app template and leaves it running on your machine. Ask it to call the method from your TypeScript or Python code, and /pipelex-integrate generates the method's types and one typed call that runs it, through the TypeScript SDK @pipelex/sdk or the Python SDK pipelex-sdk. Any other software runs a method via API through POST /v1/start, with any HTTP client.

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

Prefer to run it yourself? The Pipelex runtime runs your methods on your own machine — it and the rest of our repositories are listed below.

A method is a reusable, typed AI procedure, written in MTHDS, an open standard, and saved as a .mthds file. Each step is explicit, each output is structured, and every run is repeatable.

domain    = "articles"
main_pipe = "summarize_article"

[pipe.summarize_article]
type        = "PipeLLM"
description = "Summarize an article for a given audience"
inputs      = { article = "Text", audience = "Text" }
output      = "Text"
prompt      = "Summarize $article in three bullet points for $audience."

From here, Pipelex handles model routing across providers, structured output parsing, and pipeline orchestration.

The Pipelex runtime runs methods on your own machine, against the model providers you choose or a local model; its README carries the install, the configuration and the first run. pipelex-api is the runner API you host yourself, and the editor extension highlights and checks .mthds files, from the VS Code Marketplace or the Open VSX Registry for Cursor, Windsurf and other VS Code forks.

Build and run your methods

Run it yourself

Methods and examples

The MTHDS standard

Libraries

• Discord: get help, share methods, meet the team
• Documentation: guides and reference
• GitHub Issues: report bugs and request features
• security@pipelex.com: security and privacy concerns

The runtime and the servers that run methods — pipelex, pipelex-api and pipelex-mcp — are source-available under the Elastic License 2.0 (ELv2). You may embed them in your own products, including services whose features run your methods, and run them for your own team or company; what the license rules out is hosting a service that runs methods for others. The license page explains how we read it, with concrete examples. Every version of them released before the switch stays under MIT.

The SDKs, the starter templates, the public method library, the cookbook, the UI libraries, the VS Code extension, the n8n node, cocode and the MTHDS open standard are MIT licensed. kajson and pipelex-plugins are licensed under Apache 2.0. Each repository's LICENSE file carries its terms.

"Pipelex" is a trademark of Evotis S.A.S.