Buy-Box
Server Details
Stores your buying criteria by category so AI agents follow your rules before they search.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- tthompson0808/buy-box-cursor-plugin
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- Buy-Box
TDQS
Scored across 7 tools
The seven tools mostly target distinct lifecycle actions: get, set, delete, list, score, export, and feedback. The main overlap is get_buy_box vs export_buy_box, since both retrieve the same saved box, though their output purposes differ. score_candidates is clearly separate because it evaluates listings rather than retrieving criteria.
All tool names follow a consistent snake_case verb_noun pattern: get_buy_box, set_buy_box, delete_buy_box, export_buy_box, list_categories, score_candidates, send_feedback. There are no mixed conventions or vague names. The pattern is predictable and readable.
Seven tools is well within the appropriate 3-15 range for this server's scope. Each tool maps to a distinct operation in the buy-box lifecycle. No tool appears redundant or like filler.
The surface covers the full buy-box lifecycle: set creates or updates, get and export read, delete removes, list_categories enumerates stored categories, score_candidates applies the criteria, and send_feedback handles user feedback. Concurrency and confirmation details are addressed through expected_revision and confirmation guidance. No obvious operation is missing for the stated domain.
Available Tools
7 toolsdelete_buy_boxDelete buy boxCDestructiveInspect
Remove the buy box for a category.
Inputs: category (required).
export_buy_boxExport buy box as textBRead-onlyInspect
Return a buy box as readable Markdown the user can read or save.
Inputs: category (required).
get_buy_boxGet buy boxARead-onlyInspect
Retrieve the saved buy-box criteria for a category (homes, cars, or any freeform name).
Call this before searching or filtering. _meta.requires_confirmation is always true: surface the criteria and get explicit user confirmation before acting on results.
Inputs: category (required).
list_categoriesList buy box categoriesARead-onlyInspect
List all categories that have a buy box defined.
Inputs: no named parameters.
score_candidatesScore and rank candidatesARead-onlyInspect
Check a list of listings against a saved buy box and rank them. Pass each listing as an object with whatever fields you scraped (price, mileage, year, seats, a description, etc.).
Numeric rules (max_X, X_max, min_X, X_min) exclude listings that break them.
dealbreakers found in the listing text exclude it.
must_haves, nice_to_haves, preferred_brands_or_models and target_X / X_target score the listing.
Anything the listing doesn't state is 'unknown', not a pass: verify those with the seller's data before recommending. Excluded listings are returned last with the rule they broke. Show the user the ranked results and get confirmation before acting.
Inputs: category (required), listings (required).
send_feedbackSend feedback to the Buy-Box teamAInspect
Send a bug report, idea or comment about Buy-Box itself to its developers. Use it only when the user asks to leave feedback. Send only what the user wrote or approved, and show them the text first. Never attach their buy box contents or other personal details. At most 10 per day.
Inputs: message (required), kind, contact.
set_buy_boxCreate or update buy boxADestructiveInspect
Create or update the buy box for a category. Any field names are allowed.
Call get_buy_box first and REUSE the field names already in the box.
criteria: fields to set; each value you send replaces that field's value. A value of null deletes that field.
add: {field: [items]} appends items to any list field (created if missing, duplicates skipped). Use this to add one item without resending the whole list.
remove: {field: [items]} removes items from a list field (case-insensitive for text).
remove_fields: [field, ...] deletes whole fields.
replace=true: start from an empty box instead of merging. Order within one call: remove_fields, then criteria, then add, then remove. Server fields (_meta, requires_confirmation, last_updated) are ignored in criteria.
expected_revision: pass _meta.revision from your last get_buy_box so you don't overwrite another agent's change. If the box changed since, nothing is saved and the error returns the current box: re-read it and ask the user before writing again if a field you were changing was changed. Use 0 to create a box only if it doesn't exist. Field names are normalized to snake_case. If a new field looks like an existing one (e.g. max_miles vs max_mileage), it is saved and _meta.warnings names the existing field: tell the user and fix it with remove_fields. Do not store health details, account numbers, or passwords. Returns the saved box.
Inputs: category (required), add, remove, replace, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
One place for your preferences, portable across every AI assistant and agent.
Lets AI agents find, try and buy software inside a budget you set. No passwords or card numbers.
Persistent shopping memory for AI assistants. The AI reasons; Kaufliste stores and executes.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables an AI agent to browse inventory and make purchases under strict human approval, with hard spending caps and auditable on-chain payment records.MIT
- AlicenseAqualityDmaintenanceEnables AI agents to create, compare, and track purchases with structured buying workflows, offer comparison, and merchant verification.548 PyPIMIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to search and compare products across multiple retailers, build carts, and propose purchases that only a human can authorise, with a self-hosted control panel.-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to browse product catalogs and make purchases through a policy engine that enforces spending limits, requires human approval for certain amounts, and logs all actions to an audit trail.-
Glama MCP Gateway
Add one secure layer between your agents and this server.