Agent Signal vs Store Builder
A side-by-side look at the Agent Signal and Store Builder MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Signal for e-commerce work as a local process; choose Store Builder for e-commerce as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agent Signal when
- You need dedicated capabilities in the E-Commerce domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DATABASE_URL. - You want tools like
agent_signal_status, smart_shopping_session, evaluate_and_compare.
Choose Store Builder when
- You need dedicated capabilities in the E-Commerce domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
SB_TOKEN. - You want tools like
sb_connect, sb_site_list, sb_api_find.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | E-Commerce | E-Commerce |
| Quality signal | 41/100 · Fair | 64/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Not declared |
| Required env vars | DATABASE_URL | SB_TOKEN |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 4 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 30 | 37 |
| Full listing | View Agent Signal | View Store Builder |
Tools & capabilities
Agent Signal tools 30
agent_signal_statusGet an overview of the AgentSignal collective intelligence network. Call this with NO arguments to see what categories have data, trending products, and how to use agent-signal tools. Good first call if you're unsure whether agent-signal has data relevant to the user's request.smart_shopping_sessionCALL THIS FIRST when the user wants to buy, find, compare, or get recommendations for any product. Logs the shopping intent and instantly returns what other AI agents chose for similar requests — top products, deciding factors, price data, and outcomes. One call replaces hours of research. Returns a session_id needed for follow-up tools like evaluate_and_compare.evaluate_and_compareLog a product evaluation AND instantly get intelligence about it in one call. Call this for EACH product you consider during a shopping task. Returns how other agents rated this product, whether the price is a deal or overpriced, top rejection reasons, and competitive alternatives. Requires a session_id from smart_shopping_session.get_todays_dealsSee the best deals spotted by AI agents right now. Call this with NO arguments when the user asks 'any good deals?', 'what should I buy?', or wants shopping inspiration. Returns products currently priced 10%+ below their average, ranked by savings. Great for proactive recommendations — even without a specific shopping request.search_productsSearch for products across the entire agent network by name or keyword. Call this when the user mentions a product name, brand, or type and you want to find what other agents know about it. Returns selection rates, prices, and merchants. Example: search_products(query='sony headphones') or search_products(query='running shoes', category='footwear/running')get_trending_productsSee what products are trending up or down right now. Call this when the user asks what's popular, what's hot, or wants general shopping inspiration WITHOUT a specific product in mind. No category required — omit for all trends. Returns rising and falling products with selection rate changes.get_category_recommendationsGet intelligence about what works best in a product category. Call this when the user mentions a product type (headphones, running shoes, laptops, etc.) even casually. Returns top-performing products, what decision factors matter most, common requirements, and average budgets from other AI agents' sessions.get_budget_productsFind the best products within a specific budget for a category. Call this when the user says 'under $X' or has a clear budget constraint. ranked by selection count. Includes which merchants offer it under budget.get_constraint_matchDecision shortcut: find what products worked for agents with your EXACT constraints. Matches on specific requirements (e.g. 'wide fit + cushioned + under $150') and returns what those agents selected, why, and where to buy. Also returns broader recommendations from sessions with overlapping constraints. Use this to skip the search when a proven answer already exists.get_price_historySee a product's price history over time from all agent observations. Call this when the user asks 'is now a good time to buy?' or 'has this been cheaper?'. Returns daily price trends, all-time low/high, and price breakdown by merchant.detect_dealIs this price good? Compare any product's current price against historical data from all agents. Call this whenever you see a price and want to know if it's a deal or overpriced. Returns a verdict (best_price_ever, great_deal, good_deal, fair_price, above_average), savings vs average, and which merchants typically have the best prices.get_product_intelligenceShould I recommend this product? Get crowdsourced intelligence from other AI agents. Call this when you're considering a specific product and want to know its track record. Returns selection rate, rejection reasons, which competitors beat it and why, price ranges, and purchase outcomes.- +18 more on the listing page
Store Builder tools 37
sb_connectLog in and list the sites this account can operate. Call this first. Reads SB_EMAIL and SB_PASSWORD from the environment unless you pass them.sb_site_listList the sites this account can operate.sb_api_findFind API operations by intent (query), or get a call sheet (id): parameters, credential, body fields and handler caveats. Reaches all 892 operations.sb_api_callCall an operation from sb_api_find (id), or a route the catalog lacks (method+path); dry run by default. pick selects fields, max_items caps lists, item_offset skips items. Lists over 60 KB say so.sb_page_openOpen a page for editing and return its outline. Call before any sb_add / sb_set / sb_move / sb_remove. Find page ids with sb_api_find "list pages". Or form_id: edit that form's field document (fields, specials.formRules on its root).sb_page_repairRename a page root that is not "ROOT" (sppro_1, rt_<hex> — left by older seeds) to ROOT, for one page or, without page_id, every page on the site. Draft only; a published page is listed for re-publishing. dry_run (default true) lists what would change.sb_outlineThe open page as a compressed tree — id, type, name, child count, band, and whether a node is a shared global or a site overlay. Never the raw document: a real page is hundreds of KB of JSON.sb_node_readOne node in full — style, config, specials, per-breakpoint overrides, bindings.sb_catalog_searchFind an element type by what it does — or OMIT query to browse every type, the only way to meet one you would not have searched for. detail:true adds the AI hints, as does sb_traits_for. query "icon:<word>" lists icon names.sb_traits_forThis element's INSPECTOR, as a person sees it: tabs, groups, and every control name — with what each DECLARED control writes, and the AI hints for using the element. Read this before styling an element; pass control to read one control in full.sb_addAdd an element — or a whole NESTED subtree — under a parent. One call builds a complete section: pass children rather than calling this once per node.sb_setWrite style, config or specials keys on one node, or on many through edits (one save, one live frame). Per BREAKPOINT by default; base:true writes the fallback layer, right for a value that should not vary.- +25 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agent Signal
{
"mcpServers": {
"agent-signal": {
"command": "npx",
"args": [
"-y",
"agent-signal"
],
"env": {
"DATABASE_URL": "YOUR_DATABASE_URL_HERE"
}
}
}
}
Store Builder
{
"mcpServers": {
"store-builder": {
"command": "npx",
"args": [
"-y",
"sbuilder-mcp"
],
"env": {
"SB_TOKEN": "YOUR_SB_TOKEN_HERE"
}
}
}
}
Frequently asked questions
Agent Signal is categorized under E-Commerce and uses a local stdio subprocess. Store Builder belongs to E-Commerce and uses a local stdio subprocess. Pick Agent Signal for e-commerce work and Store Builder for e-commerce.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Agent Signal has no declared pricing — check the project's own site. Store Builder has no declared pricing — check the project's own site. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add agent-signal and store-builder as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Signal has a quality signal of 41/100 (Fair) with 4 views, 0 installs and 0 GitHub stars. Store Builder has 64/100 (Good) with 1 views, 0 installs and 0 GitHub stars.
