Pulltrader

app.pulltraderPublished by pulltrader.appOfficial publisherv0.6.1Updated Oct 25, 2026

Trading-card research and seller economics: identify cards, check sold comps, and compare fees.

VerifiedStreamable HTTPWeb executableFinanceBusiness & Commerce

Overview

AI-generated overview

A public, read-only trading-card research server: identify cards, pull sold comps, chart price history, and estimate seller fees and net proceeds.

What you can do
Identify a card from a text description and return structured fields with a confidence level, without pricing it. Retrieve a capped sample of recent comparable sold sales and a market snapshot, or a summarized market value with median, mean, percentile range, volatility and confidence. Get a chart-ready price history by day, week or month with a trend. Compare estimated fees and net proceeds across selling methods, including eBay and Pulltrader channels, with a per-method breakdown. Solve for the sale price needed to reach a target take-home or net profit, and explain how each selling method handles listing, fulfillment and fees. Check a Kapture certificate number against a stolen-card list.
When to use it
Useful for trading-card sellers, dealers, shops and collectors who want to know what a card is, what it recently sold for, and what they would keep after fees, without leaving the assistant. Best suited to quick research and fee comparisons on text-described cards in USD.
Requirements
A remote Streamable HTTP endpoint; no local install or package. The README states the public endpoint needs no authentication, though the manifest declares OAuth as required. Card data tools depend on a backend bridge; without it they return a data-backend-unavailable error. Rate limits apply per IP and globally. Trading cards and USD only.
Before you install
Market values and eBay fee figures are estimates, not guaranteed values or financial advice; eBay estimates exclude promoted listings, international fees, sales tax and shipping-label costs. The server is described as read-only and makes no writes, orders or account changes. Card data is a limited public sample with no per-listing or affiliate URLs. A clean stolen-card result only means no verified report matched.

Installation

In SourceWeft

  1. Open Pulltrader in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/app.pulltrader%2Fseller-economics/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "pulltrader": {
      "type": "http",
      "url": "https://mcp.pulltrader.app/mcp"
    }
  }
}

README

Pulltrader — Trading-Card MCP Server

Identify a card, pull recent sold comps, summarize its market value, chart its price history, and compare what a seller keeps across eBay, Pulltrader, and other card marketplaces — inside your AI assistant.

A public, read-only Model Context Protocol server for trading-card research and selling. Eight tools: a Kapture stolen-card registry check, four back onto Pulltrader's card data (identification, comparable sold sales, market value, price history), three run Pulltrader's deterministic seller-economics engine over a dated, versioned fee schedule.

Market figures are estimates derived from recent sales. Fee math is deterministic — the server computes it and never asks the model to infer fees from prose. eBay figures are clearly labeled estimates.

  • Transport: Streamable HTTP (POST /mcp)
  • Auth: none (public, read-only)
  • Endpoint: https://mcp.pulltrader.app/mcp
  • Registry name: app.pulltrader/seller-economics
  • Protocol: 2025-06-18 (the client's requested version is echoed when present)

Who it's for

Trading-card sellers, dealers, shops, and collectors who want to know what a card is, what it's worth, and what they'd actually take home selling it — without leaving their assistant.

What it does (and doesn't)

DoesDoesn't
Resolve a prose card description into structured fieldsIdentify a card from an image (text only)
Return recent comparable sold sales (price + date)Return listing, affiliate, or per-sale outbound URLs
Summarize market value: median, mean, p10–p90, volatility, confidenceClaim a guaranteed value or give financial advice
Chart price history by day / week / month with a trendMake any write, order, or account change
Estimate seller fees and net proceeds per selling methodClaim one platform is universally cheapest
Solve for the price needed to hit a target netModel auction formats (hammer, buyer's premium, consignment)
State its assumptions, data freshness, and limitationsCover non-card categories or currencies other than USD

Tools

Kapture cert check (data-backed)

check_kapture_cert accepts { "cert": "00123456" } and preserves leading zeros. CLEAN only means no verified stolen report matched. STOLEN includes the Kapture report and a voluntary Pulltrader recovery-form link. The tool never collects personal information, infers possession, or submits a recovery report. The backend holds KAPTURE_API_KEY; no new Worker secret is needed. Recovery handoff is manual until Kapture provides a reporting API. See pulltrader-backend/docs/KAPTURE.md.

Card research (data-backed)

These bridge to the Pulltrader backend. Card data is limited-public: a capped sample of sales, no per-listing or affiliate URLs, and only the catalog reference image.

Each accepts either query (a natural-language description, e.g. "2023 Panini Prizm Victor Wembanyama #136 Silver PSA 10") or item (structured fields: player_athlete, year_manufactured, set_name, card_number, parallel_variety, grader, grade, sport). One of the two is required.

ToolWhat it returns
identify_cardCanonical fields (player/athlete, year, set, number, parallel, grader, grade, category) plus a confidence level and which fields resolved. Takes query only. Does not price the card.
search_card_salesA capped sample of recent comparable sold sales (price + date) plus a market snapshot. Optional limit.
summarize_card_marketCanonical market value: median, mean, p10–p90, volatility, sample size, confidence.
get_card_price_historyA chart-ready time series with a trend. Optional interval: day | week | month.

When eBay has no dated comps, search_card_sales and summarize_card_market fall back to the authoritative vendor price and surface market_value, value_source (TCG Market | CardSightAI | eBay Comps), price_change_7d, price_change_30d, and a single catalog image.

Seller economics (deterministic, no I/O)

ToolWhat it returns
compare_selling_costsEstimated fees and net proceeds for one sale across selling methods, with a per-method fee breakdown, the difference vs the eBay baseline, and the assumptions used. Requires sale_price.
calculate_required_sale_priceThe per-item price needed to reach a target take-home (or net profit, when acquisition_cost is given) on a single method. Requires target_net.
explain_selling_methodPlain, structured explanation of how each method owns the listing, fulfills, and charges fees. Derived from the same engine, so it never drifts from compare_selling_costs.

Shared inputs (compare_selling_costs, calculate_required_sale_price):

FieldTypeDefaultNotes
currencyenum USDUSDOnly USD supported
quantityinteger1Per-order fixed fees applied once
shipping_amountnumber0Affects eBay's fee base
item_categoryenum trading_cardstrading_cardsOnly trading cards
seller_planfree|starter|pro|shopfreeMarketplace payout tier
seller_levelenumderived from planExplicit payout level override
seller_covers_feesbooleanfalseIf false, the buyer pays the platform fee
ebay_store_subscriptionbooleanfalseeBay Store rate (12.35%) vs individual (13.25%)
acquisition_costnumber—Switches output to net profit
ebay_fee_percent_overridenumber—Override the estimated eBay FVF % (flat)

Supported methods: ebay, pulltrader_marketplace, pulltrader_fbp, pulltrader_storefront, pulltrader_pos, plus estimated competitor marketplaces tcgplayer, manapool, misprint, fanatics_collect, goldin (off by default — opt in via methods). Competitor figures model fixed-price / Buy Now seller fees only.

Example prompts

  • "What is this card: 2023 Bowman Chrome Elly De La Cruz PSA 10?"
  • "Show me recent sold comps and the market value for that card."
  • "What's the price history on a 2018 Prizm Luka Doncic Silver PSA 10 over the last year?"
  • "Compare my estimated proceeds on a $250 graded-card sale."
  • "What would I keep on an $80 card on eBay vs Pulltrader?"
  • "What do I have to sell it for to clear $200 after fees?"
  • "Explain the assumptions behind this payout estimate."

Example response (text summary)

On a $250.00 trading-card sale, estimated seller proceeds by method:- Sell it yourself on eBay: keep $216.47 (estimated) (fees $33.53, 13.41%)- Pulltrader marketplace (you ship): keep $235.00 (fees $15.00, 6%)- Your Pulltrader storefront (you ship): keep $250.00 (fees $0.00, 0%)For these inputs, Your Pulltrader storefront (you ship) returns about $33.53 more than Sell it yourself on eBay.Estimate based on fee schedules updated 2026-06-01 (Pulltrader) and 2026-06-27 (eBay, estimated). Estimates only, for trading cards in USD. ...

eBay = 13.25% individual FVF + $0.40 per-order fee (orders over $10). The storefront keeps 100% because Pulltrader has no seller fee on storefront/POS — only the platform fee, paid by the buyer here. The platform fee is always charged on Pulltrader card sales (buyer pays by default).

Connecting

Claude (web / Desktop)

Settings → Connectors → Add custom connector → URL https://mcp.pulltrader.app/mcp.

ChatGPT

Settings → Apps & Connectors → Advanced → enable Developer mode → Create → URL https://mcp.pulltrader.app/mcp.

Cursor / generic

Add to your MCP client config:

json
{  "mcpServers": {    "scout-by-pulltrader": {      "url": "https://mcp.pulltrader.app/mcp"    }  }}

Tested clients: Claude (web/Desktop), ChatGPT developer mode, Cursor, MCP Inspector. We do not claim universal compatibility with every assistant.

Public access & rate limits

The /mcp endpoint is public and read-only. A separate seller resource is implemented at /seller/mcp; OAuth is provisioned and its signed-in pilot is pending. See Seller MCP.

LimitDefaultNotes
All POST /mcp60 / IP / minHTTP 429 + Retry-After. Fail-open if KV is down.
Data tools (identify / comps / market / history)8 / IP / min, 40 / IP / dayTool isError RATE_LIMITED. Fail-closed if KV is down.
Data tools global10,000 / dayCircuit breaker for model + comps spend.
Batch size5 messagesLarger batches are rejected.

Requires the MCP_ABUSE KV namespace (see wrangler.toml). Tune via PUBLIC_RATE_LIMIT_PER_MIN, DATA_RATE_LIMIT_PER_MIN, DATA_RATE_LIMIT_PER_DAY, DATA_GLOBAL_LIMIT_PER_DAY.

Errors

Input problems come back as a tool result with isError: true and a stable code, not a JSON-RPC error: INVALID_INPUT, NOT_FOUND, RATE_LIMITED, UPSTREAM_ERROR, UPSTREAM_TIMEOUT, DATA_BACKEND_UNAVAILABLE, INTERNAL_ERROR. Unknown methods and malformed envelopes use standard JSON-RPC error codes.

The four card tools require the backend bridge (PULLTRADER_API_BASE + SCOUT_MCP_SECRET). Without it they degrade to DATA_BACKEND_UNAVAILABLE; the three seller-economics tools are pure and always available.

Data sources & fee freshness

  • Card data is limited-public and estimate-only: a capped sample of recent sold comps, aggregated by the shared Pulltrader domain engine.
  • Pulltrader fees mirror Pulltrader's authoritative internal fee configuration.
  • eBay fees are an estimate of published trading-card rates (tiered individual/Store final value fee + order-size-based per-order fee), updated and reviewed on a schedule. See docs/FEE_SCHEDULES.md. Responses warn if a schedule is past its review date.

Current schedule versions are served live at /version.

Limitations

  • eBay estimates exclude promoted listings, international fees, buyer-paid sales tax, and the seller's own shipping-label cost.
  • Market values are estimates from recent sales, excluding fees, taxes, and shipping.
  • Not financial advice; actual proceeds and actual value vary.
  • Trading cards / USD only in this release.

Development

bash
npm installnpm run typecheck   # tsc --noEmitnpm test            # vitestnpm run dev         # wrangler dev (local)

Deploy and registry submission require explicit approval — see docs/DEPLOYMENT.md and docs/DISTRIBUTION.md. Do not deploy or publish from a development session.

More

Deploy prerequisites

bash
wrangler kv namespace create MCP_ABUSEwrangler kv namespace create MCP_ABUSE --preview# Paste ids into wrangler.toml [[kv_namespaces]] binding MCP_ABUSEwrangler secret put SCOUT_MCP_SECRET

Roadmap

  • Image-based card identification.
  • Athlete/player profile tools.
  • Complete the signed-in seller pilot for /seller/mcp; global per-user quotas remain future work.

Built and maintained by Pulltrader. Support: [email protected]

This repository is the public mirror of the Pulltrader MCP Worker, exported from the Pulltrader monorepo on each release. Issues and questions are welcome here; pull requests are applied upstream. wrangler.toml KV ids are redacted — deploys run from the monorepo.

Source: README.md at commit 722bd35

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v0.6.1LatestOct 4, 2026
  2. v0.2.2Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts