Skip to content
Slabline logo

Slabline MCP server

Which MCP servers are Slabline's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to Slabline

Whose server it is
  • Registry nameai.slabline/slablineverified in the MCP registry

The registry name sits under slabline.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools4
  • Server calls itselfslabline
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 132 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-29
  • INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
  • Answered100% of days7 of 7 daily checks
  • Median first answer163 ms
  • Space in an agent's context≈ 400 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · check the value of a graded card by cert number
  • not sure · decide whether a raw card is worth grading
  • cannot · track insurance coverage across a slab collection

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-29
  • search_cards

    Search Slabline's catalogue of 1.5M+ graded cards (PSA/BGS/SGC/CGC) by player, set, or year. Returns up to 10 matches with their current Slabline value, highest-value first.

  • value_card

    Get one card's current Slabline value: graded market value, raw/loose value, and the across-grades total. Pass a slug from search_cards, or a free-text query (the top match is used). Values are Slabline-derived from real comparable sales…

  • search

    Search Slabline for graded trading cards (sports & TCG) by player, set, or year. Returns matches, each with an id to pass to fetch.

  • fetch

    Fetch one Slabline card by id (the slug returned by search): its current graded market value, raw/loose value, and across-grades total.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "slabline": {
      "type": "http",
      "url": "https://slabline.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http slabline https://slabline.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://slabline.ai/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.