canonical: https://jentic.com/apis/compsapi.com/compsapi # CompsAPI The CompsAPI API returns real eBay sold prices as structured JSON, with up to three years of sales history and real accepted Best Offer prices. It serves sold listings newest-first for a search and a comps endpoint that computes price statistics alongside the ten most recent matching sales. A dedicated trading-card layer covers graded cards, so an agent can price a specific collectible from what it actually sold for rather than from asking prices. ## For AI agents Search eBay sold listings and pull price statistics and recent comparable sales for an item or graded trading card. The data operations are read-only GETs taking an API key or bearer token. ## Scope Does not handle listing items for sale, payment processing, or inventory management. Use for looking up eBay sold prices and trading-card comps only. ## Capabilities - Search eBay sold listings for a query and read them newest sale first - Compute price statistics plus the ten newest matching sales for a card or item - Price graded trading cards from real accepted sale prices, including Best Offer figures - Read up to three years of sold-price history for a search - Check the current UTC-day usage without spending against the request allowance ## Use cases ### Trading-Card Price Comps A reseller agent prices a graded trading card by reading real accepted sale prices rather than optimistic listing prices. CompsAPI returns price statistics and the ten newest matching sales from eBay, including accepted Best Offer figures, so the agent can set an ask that reflects what the card actually trades for. Example prompt: Call GET `/v1/comps` for a specific graded card to read its price statistics and the ten most recent comparable sales ### Resale Price Research Before listing an item, an agent searches CompsAPI for completed eBay sales matching the product and reads them newest sale first across up to three years of history. This grounds a resale decision in real transaction data, including accepted Best Offers that ordinary search results hide. Example prompt: Call GET `/v1/sold` for a product search and read the completed sales newest first to estimate resale value ### AI Agent Integration via Jentic An AI agent reaches CompsAPI through Jentic without handling the API key itself. It searches by intent, receives the matching operation and its input schema, and executes the call with the credential injected at run time. This lets the agent fetch sold-price comps as a grounding step before it drafts a listing or answers a valuation question. Example prompt: Search Jentic for 'eBay sold prices', load the GET `/v1/sold` schema, and execute it with Jentic-managed credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/v1/sold` | Sold listings for a search, newest sale first | | GET | `/v1/comps` | Price stats plus the ten newest matching sales | | GET | `/v1/usage` | Usage for the current UTC day | | GET | `/v1/health` | Service status | ## Key resources - **Sold listings** — Search completed eBay sales for a query, newest first, via `/v1/sold` - **Comps** — Read price statistics plus the ten newest matching sales via `/v1/comps` - **Usage** — Read the current UTC-day usage, which does not count against limits, via `/v1/usage` ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 46 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 93 / 100 - Developer Experience & Jentic Compatibility: 61 / 100 - AI-Readiness & Agent Experience: 22 / 100 - Agent Usability: 94 / 100 - Security: 55 / 100 - AI Discoverability: 63 / 100 - **View full report:** https://jentic.com/apis/compsapi.com/compsapi/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring CompsAPI by hand means managing its API key, choosing between the X-API-Key header and a bearer token, and handling your daily usage window yourself. Through Jentic you install once, import CompsAPI from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** This API is read-only: it serves only GET lookups against sold-price data, so a rule can confine your agent to reading prices and nothing that changes state. You choose which of the reads it may call, so the sold-listings and comps lookups can be allowed while the usage check is withheld. - **Credential handling:** Your CompsAPI key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'eBay sold prices' or 'trading card comps', and Jentic returns the matching CompsAPI operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **eBay** — eBay's own APIs cover live listings and selling, not a packaged sold-price comps feed - **Pokemon TCG API** — Card metadata and set details for Pokemon trading cards - **TCGdex** — Multilingual trading-card database for card identifiers and imagery ## FAQ ### What authentication does the CompsAPI use? The CompsAPI authenticates with an API key sent in the X-API-Key header, or alternatively a bearer token in the Authorization header, per its OpenAPI spec. The health endpoint is open and needs no credential. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent. ### Can I price a graded trading card with the CompsAPI? Yes. The comps operation returns price statistics plus the ten newest matching sales for a card, including real accepted Best Offer prices, so an agent can value a graded card from what it actually sold for. The sold-listings operation adds the fuller completed-sales history behind that figure. ### What are the rate limits for the CompsAPI? The OpenAPI spec does not publish specific rate-limit numbers; check https://compsapi.com/docs for the current limits on your plan. The usage operation reports your consumption for the current UTC day and does not itself count against the allowance, so an agent can check where it stands before a batch of lookups. ### Is there a CompsAPI MCP server? You don't need an MCP server to give your agent CompsAPI. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the sold-price and comps operations. Nothing extra is loaded into the agent's context until an operation is actually invoked. ### Can I limit what my agent is allowed to do with the CompsAPI? Yes. CompsAPI is read-only, so write a rule that allows only the lookups it needs, for example the sold-listings and comps reads, and the agent can research prices and nothing else. Because every call runs through your own Jentic One instance, each one is logged for you to review. ### How do I look up sold prices with the CompsAPI through Jentic? Search Jentic for 'eBay sold prices', and it returns the CompsAPI sold-listings operation with its input schema. Load the schema and execute GET `/v1/sold` with your search terms and the credential injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.