Add Ecommerce Agent Starter to AI & MCP Servers - #79
Open
luispintoapify wants to merge 1 commit into
Open
luispintoapify wants to merge 1 commit into
luispintoapify wants to merge 1 commit into
Conversation
Placed first in the section, since "Ecommerce Agent Starter" precedes "PayPal Agent Toolkit" alphabetically. Canonical repository URL with no tracking parameters, per the entry rules.
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
Ecommerce Agent Starterto AI & MCP Servers: an MIT-licensed Python starter that connects an AI agent to live retailer product data over MCP, which is the read side of the same job the PayPal and Stripe entries in that section cover for payments.Disclosure: I work on e-commerce product marketing at Apify, and the starter calls an Apify Actor. Flagging it against the self-promotion line in the guidelines rather than leaving it to be discovered. What I would offer as the case for inclusion is that the repo is mostly the part that is useful whoever you buy the data from: per-retailer field maps built from real captured output, the two-and-sometimes-three-call MCP fetch flow written down, and a benchmark of three approaches over twenty questions frozen before any of them ran, with every result file committed so the numbers can be rescored rather than taken on trust. It also documents where the approach does not work, including a measured median latency of 24 seconds and a locale failure that returns the wrong currency.
Alphabetically first in the section. Canonical repository link, no tracking parameters. Nothing else in the file touched.