NorthCinder MCP server
Commit Aug 22, 2026Enables AI agents to compare products from multiple sources and request buyer approval before making purchases.
Also known as cinderline/northcinder
- Stars
- 1,201
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Aug 22, 2026
- License
- MIT
What is NorthCinder MCP?
NorthCinder enables AI agents to compare products from multiple sources and request buyer approval before making purchases.
Summary generated from the project's README
About NorthCinder MCP server
Comparing products from multiple independent sources and managing buyer approvals is what NorthCinder enables for AI agents. Instead of relying on a single marketplace that steers users toward specific checkouts, this software runs alongside your AI application to provide neutral comparisons. It works locally using Node.js 20 or later, and in local mode, it operates without API keys by running the search engine and MCP server together via a temporary loopback port.
Developers can connect the server to various stores including Shopify, WooCommerce, eBay, Etsy, and Amazon. The system prioritizes transparency by showing why specific products were ranked or rejected. To ensure security, the tool requires a fresh, signed approval for every single purchase, including the merchant, price, and spending cap. It avoids handling raw credit card details, instead using opaque payment tokens or providing cart links for manual completion in a browser.
For remote setups, users can configure a service using NORTHCINDER_API_KEYS, NORTHCINDER_SERVICE_URL, and a NORTHCINDER_CLIENT_KEY. All audit logs, recommendations, and purchase approvals remain on your local machine to maintain privacy.
What you can do with it
- 1Compare multi-source product optionsAsk an AI agent to find specific items like black wool running shoes and compare their price, delivery, and merchant trust across different stores.
- 2Execute structured product researchUse the create_research_plan tool to build a checklist for verifying product details and seller information before making a recommendation.
- 3Securely approve automated purchasesProvide a single-use signed approval for a specific product variant and price to allow an agent to complete a checkout.
- 4Audit shopping recommendationsReview local logs to inspect the ranking specifications and ensure sponsored offers are not being prioritized over organic results.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablecinderline/northcinder is public and reachablegithub.com/cinderline/northcinder ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-22github.com/cinderline/northcinder ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubNorthCinder
Your shopping agent should work for you.
AI agents are starting to do more than answer shopping questions. Soon they will decide which products people see and, in some cases, buy on their behalf.
Big marketplaces are building the easiest version of this: an agent that searches one catalog and steers the buyer toward that platform's checkout. That may be convenient, but it is not independent advice. The marketplace still decides what can be seen and makes money when the agent closes the sale.
NorthCinder takes a different approach. It compares products from the sources you choose and shows where its facts came from. Before it buys anything, it asks for your approval. NorthCinder is software you run alongside your AI app.
The repository owner does not operate a NorthCinder service. There is no NorthCinder account or cloud service.
Get started
You need Node.js 20 or later and an MCP-capable AI app.
npx northcinder init
The command saves your configuration on your computer and prints the MCP entry for your AI app. Local mode is keyless. It runs the MCP server and search engine together in one process, using a temporary loopback port.
Once connected, try a real shopping brief:
Find black wool running shoes under $130. Compare price, delivery, fit, and merchant trust. Tell me why the winner ranked first and which options were ruled out.
What a result looks like
NorthCinder does not pretend there is one universal "best" product. It normally shows no more than three useful choices: the strongest fit, a lower-risk option, and a cheaper or meaningfully different option when one exists.
Each result explains why it ranked where it did. You can also inspect the other finalists, rejected offers, and facts that could not be verified.
Research before recommendation
Product research gets messy quickly. Model names overlap, sellers copy one another, and a polished product page can hide the one detail that makes an item wrong for the buyer.
NorthCinder includes separate research guides for products and sellers. Before doing the research, the MCP host should:
- Read
northcinder://research/productornorthcinder://research/seller. - Call
create_research_planwith the actual request and exact subject. - Follow the returned checklist with the research tools it already controls.
If the sources disagree or do not identify the exact product or seller, the result stays provisional. Research can decide whether an offer is ready to compare, but it cannot add ranking points.
No host and model combination is currently qualified for routine research use. Treat every research result as provisional until the buyer checks its identity, sources, conflicts, and unknowns.
Buying stays a separate decision
A recommendation is not permission to buy. Every checkout needs a fresh approval for one exact offer and one unit. The signed approval includes the merchant, variant, price, known total, and spending cap. It can be used once.
NorthCinder rejects raw card details. A supported automated checkout can use an opaque payment token, or NorthCinder can hand the buyer a cart link to finish in their own browser.
Order outcomes stay local and only attach to the purchase they belong to. NorthCinder does not silently rewrite the buyer's profile, and its reminders only send notifications.
Rules you can inspect
Seller payment never improves ranking. Sponsored offers stay labeled and below organic results. Missing store coverage stays visible, and unknown seller history remains unknown instead of being guessed safe or unsafe.
NorthCinder reruns the ranking locally and writes recommendations, approvals, and checkout attempts to a local audit log. The ranking specification, trust specification, neutrality audit, and checkout package contain the details.
These checks cover the offers NorthCinder received, not the completeness or truth of a store's catalog.
How NorthCinder works
Your AI app talks to NorthCinder over MCP. NorthCinder runs the search engine locally, checks the ranking before returning it, and keeps the audit log and purchase approvals on your computer. You choose the store connections. The repository owner is not part of this path.
Store coverage
Store access varies, and NorthCinder says when a store was unavailable or not configured. It does not present a partial search as though it covered the whole market.
Built-in adapters cover Shopify, WooCommerce, eBay, Etsy, and read-only Amazon comparison.
If a native connection is missing, the AI app can keep researching with its own browser or search tools. NorthCinder accepts product facts, not cookies, raw pages, passwords, or page instructions. A native connection must confirm the exact offer before checkout or an unattended watch.
Self-hosted engine
Most people should use local mode. If you choose to run the engine separately, set NORTHCINDER_API_KEYS on the service and configure the client with NORTHCINDER_SERVICE_URL and the matching NORTHCINDER_CLIENT_KEY bearer credential. Non-loopback bearer connections must use HTTPS.
Privacy
- NorthCinder never needs your AI provider key. It stays in your AI app. Store credentials stay with you and the store.
- NorthCinder does not send your searches, settings, or local history to the repository owner.
- Raw card details are rejected rather than stored or forwarded.
- Starting a search or price watch does not give NorthCinder permission to buy anything.
Read privacy and software ownership and the security policy for the full boundary.
Build from source
This is a pnpm workspace. Product packages need Node.js 20 or later. The private site workspace needs Node.js 22.12 or later.
corepack pnpm install --frozen-lockfile
corepack pnpm build
node northcinder/bin/northcinder.js init
The full release checks are documented in CONTRIBUTING.md.
Contributing and support
- Use GitHub Issues for reproducible bugs and focused proposals.
- Use GitHub Discussions for questions and early ideas.
- Report vulnerabilities through GitHub private vulnerability reporting, not a public issue.
NorthCinder is open source under the MIT License.
NorthCinder MCP questions
Does NorthCinder require an account or cloud service?
No, there is no NorthCinder account or cloud service; it is software you run alongside your AI app.
Can NorthCinder buy products automatically without permission?
No, every checkout requires a fresh approval for a specific offer and unit, including the merchant, price, and spending cap.
How does the server handle sensitive payment information?
NorthCinder rejects raw card details and can use opaque payment tokens or provide cart links for manual checkout.