Skip to main content
Glama
haksanlulz

mcp-scryfall

by haksanlulz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

card_search

Search Magic: The Gathering cards using Scryfall query syntax. Returns concise card summaries with counts; set full:true for the raw response. A 404 error means no matches.

Instructions

Scryfall query-syntax search (e.g. 'is:fetchland t:land', 'c:rb cmc<=2 t:creature', 'o:"draw a card" pow=1'). Returns compact per-card summaries plus total_cards/has_more by default to keep responses small; pass full:true for the raw Scryfall response. A query that matches no cards is NOT an empty list — Scryfall answers it with a 404, which surfaces as an error carrying Scryfall's details. That error is the answer 'no cards match'; do not retry it as a tool failure. Full syntax: https://scryfall.com/docs/syntax

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesScryfall query string
fullNoReturn the raw Scryfall response instead of compact summaries (default false)
pageNoPage number: an integer >= 1 (default 1). Any other value is an error.
orderNoSort order: name, cmc, color, released, etc. (default: name)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and excels: it discloses the compact-summary default, the full:true override, the 404-on-no-match behavior, and instructs not to retry as a tool failure. It also points to external documentation for full syntax, giving the agent complete behavioral awareness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but efficient: it front-loads the purpose and examples, then addresses output format and error handling in a few sentences. Every sentence contributes, with no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a query-language tool with complex syntax and non-standard error behavior, the description covers all essential aspects: query examples, output format options, pagination (via schema), sort order (via schema), and the 404 semantics. The link to full syntax ensures complete coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds significant value: it gives illustrative examples for the 'q' parameter and clarifies the 'full' parameter's default behavior. Page and order are adequately covered by schema descriptions, so no gap remains.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs a Scryfall query-syntax search with concrete examples, and the sibling tools card_named/card_fuzzy are implicitly distinguished by their name-based nature. The verb 'search' and resource 'cards' are explicit, making the tool's purpose unambiguous and differentiable from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for complex query-syntax searches through examples but does not explicitly contrast with card_named, card_fuzzy, or other siblings. It does provide a critical usage note about the 404 error being a valid 'no matches' result, which is a usage guideline, but lacks direct alternative-selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools