Mercadona MCP Server
Enables shopping at Mercadona online grocery store via Claude, allowing catalog search, cart management, and order history retrieval while keeping payment control with the user.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
igorsafonov-gif
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
get_shopping_guideReturn the Mercadona shopping playbook: how to present products (ALWAYS as a photo-grid artifact), fill and review the real cart, use 'my regulars', and reorder past shops. Call this once at the start of any Mercadona task — before searching or adding to the cart — and follow it.
auth_statusCheck whether the Mercadona session is valid and how long the token lasts.
loginOpen a browser window to sign in to Mercadona. The user logs in (and handles any 2FA/SCA); the session is then saved so all other tools work. Call this when not signed in, or when a tool reports the session expired.
search_productsFind a product and its id (needed before add_to_cart), scoped to the user's delivery area. Use a short term; prefer the house brand 'Hacendado' unless asked otherwise. Returns matches with ids and prices.
get_productGet details for a single product by id.
get_cartShow the current real shopping cart (items, quantities, total).
get_my_regularsProducts you usually buy. kind='precision' = most bought; kind='recall' = also bought.
get_purchase_historyList past orders (date, total, status, item count). Page is 1-based.
get_order_itemsList the products in a past order (without adding anything). Defaults to the most recent order if order_id is omitted.
get_delivery_slotsAvailable delivery slots. Uses your first address if address_id is omitted.
add_to_cartAdd a product to the real cart by id (get the id from search_products or get_my_regulars first). If already present, increases the quantity. Returns the updated cart with its total.
set_quantitySet the exact quantity of a product in the cart. Quantity 0 removes it. Returns the updated cart.
remove_from_cartRemove a product from the cart entirely. Returns the updated cart.
reorder_orderAdd all items from a past order to the cart in one step (a 'buy again'). Defaults to the most recent order. Skips items no longer available and reports them. Returns the updated cart.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
esbuild enables any website to send any requests to the development server and read the response
MERCADONA_BROWSER_CHANNEL"env": { "": "chrome" }MERCADONA_STATE_PATHOverride the location with , or the browser with MERCADONA_BROWSER_CHANNELDependencies
4 dependencies, 1 flagged: playwright-core
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
14/14 tools missing one or more hints — get_shopping_guide (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); auth_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); login (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 0/2 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
1/2 tool handlers wrap calls in try/catch (50%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/igorsafonov-gif/mercadona-claude-extension)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check