# originselect-mcp-server MCP server for OriginSelect Discovery API — search ethical, origin-verified products and brands via AI agents - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 1.0.12 - **Author:** OriginSelect - **License:** MIT - **npm:** originselect-mcp-server - **Source:** https://github.com/chhavimishra/originselect-mcp-server - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 1 day ## Security scan - **Status:** clean - **Scanned:** 2026-09-11T00:07:06.260Z - **Version scanned:** 1.0.12 - **CVEs:** none found by OSV at scan time ## Tools 19 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `get_affiliate_performance` — Affiliate clicks/conversions/orders/revenue/commission for one program+market (e.g. program="amazon", market="CA"), with per-row tracking ID/SubID/SKU and attri - `get_data_freshness` — Status, last-success timestamp, and data-through-date for every OriginSelect intelligence connector (GSC, GA4, Bing, Pinterest, Amazon US/CA/AU, Refersion, inte - `get_ctr_opportunities` — Pages/queries with a meaningful CTR gap or zero clicks relative to their search position — the "ranking fine, nobody's clicking" bucket, pulled from the current - `get_cannibalization` — Queries where multiple OriginSelect pages have meaningful overlapping search visibility (possible cannibalization), checked against currently-notable queries. - `get_page_performance` — Cross-channel performance for one OriginSelect page: search metadata, per-channel session/click/impression totals, and its top search queries. - `get_page_queries` — Search queries driving impressions/clicks to one OriginSelect page, with per-query click/impression/position/CTR. - `get_channel_performance` — Google/Bing/Pinterest/AI-referral channel summary for one page over an optional date range — sessions, clicks, impressions, outbound clicks, engagement per chan - `get_change_history` — Logged build/content changes for one page. Use alongside get_page_performance to check for correlation between a change and a performance move — the backend nev - `get_ai_referral_performance` — AI referral/click behavior (ChatGPT, Perplexity, Claude, Gemini, etc.) for one OriginSelect page over an optional date range. - `get_ranking_changes` — Meaningful search-ranking gains/losses for one page's queries over time: new visibility, gainers, decliners, lost visibility. Tiny impression counts are filtere - `get_daily_priorities` — Top OriginSelect content/traffic/revenue opportunities ranked by evidence and business value, with reason codes and score components so you can explain why one - `get_query_performance` — Search performance for one query across engines (Google/Bing) and landing pages — clicks/impressions grouped by engine, with the pages ranking for it under each - `get_query_pages` — Which OriginSelect pages are ranking/competing for one query, with each page's clicks/impressions/position. - `refine_search` - `search_brands` — Search for ethical and origin-verified brands on OriginSelect. Filter by country of origin, ethical values (women-owned, b-corp, organic, etc.), and product cat - `search_products` — Search OriginSelect's curated catalog of ethical, origin-verified products. Filter by country of origin, ethical values (e.g., women-owned, organic, b-corp), pr - `get_values` — List all supported ethical/ownership values that can be used to filter products and brands. Returns canonical value tokens with display labels. - `get_categories` — List all supported product categories that can be used to filter products and brands. - `get_countries` — List all supported countries of origin that can be used to filter products and brands. Currently supports Canada and USA. ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"originselect-mcp-server\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"originselect-mcp-server\"\n ],\n \"env\": {\n \"INTELLIGENCE_API_KEY\": \"\"\n }\n }\n }\n}" ``` **Credentials it will ask for** (names only — Forge never holds a value): - `INTELLIGENCE_API_KEY` — Intelligence API Key (optional) Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one. - This entry needs 1 credential (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset. ## Blast radius Moderate blast radius — holds an api key; runs on your machine. - Floor 23, ceiling 23 (tier: moderate) - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/originselect-mcp-server - Install plan: https://forgeregistry.com/api/v1/packages/originselect-mcp-server/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/originselect-mcp-server - HTML page: https://forgeregistry.com/registry/originselect-mcp-server - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.