CNAPS.ai MCP Server

search_cards

Read-onlyIdempotent

Search the ready-made cards on the cnaps.ai home page — flows the cnaps.ai team built, tested and published for common tasks (remove a background, restore a photo, make an ad video…). Check here FIRST when the user describes a task: a card that fits is better than building a flow from models. Matches words in any language against every card's title and description, rarer words and title words counting more. cards holds the closest few matches in full; other_cards lists more by title only, closest first, and when the matches cover only some of your words it lists every other card too — read their titles. When nothing matches, cards is every card by title (matched=false) so you can pick one by meaning. Pass a card id as query to get that card's details. Run a card with fork_card.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_cards"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Language to show card text in, e.g. 'ko' or 'en' (default en). Does not affect matching.
`query`	No	What the user wants, in their words (e.g. 'remove background', '배경 제거'), or a card id. Omit to list every card.
`input_type`	No	Only cards that take this input: image, video, text or audio.
`output_type`	No	Only cards that produce this output: image, video, text or audio.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 2, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations carry the safety profile, and the description adds substantial behavior beyond them: cross-language word matching with rarer/title words weighted higher, result partitioning into full-detail 'cards' vs title-only 'other_cards' with ordering guarantees, and a documented no-match fallback (cards = every card with matched=false). This is the kind of ranking and fallback disclosure annotations cannot express.

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

Conciseness4/5

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

Front-loaded with what the tool is and the 'check here first' instruction, and every sentence carries operational content. The middle sentence about other_cards is dense and slightly run-on, costing a bit of readability, but nothing is filler.

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?

Despite having no output schema, the description fully describes the response shape (cards, other_cards, matched flag) and ordering, so an agent can consume results without guessing. For a four-optional-param read-only search tool, nothing needed for correct invocation is missing.

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 baseline is 3, but the description adds real semantics: query is matched against title and description in any language with weighting, and a card id in query switches to a detail lookup, while omitting query lists everything. The lang-vs-matching distinction is already in the schema, so it earns 4 rather than 5.

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?

States a specific verb and resource ('Search the ready-made cards on the cnaps.ai home page') and defines what a card is — team-built, tested, published flows for common tasks. The closing 'Run a card with fork_card' separates searching from executing, and 'better than building a flow from models' distinguishes it from create_flow/find_compatible_models.

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

Usage Guidelines5/5

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

Explicit prioritization: 'Check here FIRST when the user describes a task.' It names the alternative path (building a flow from models) and the follow-up tool (fork_card), plus the card-id lookup mode. An agent knows when to call this ahead of siblings without inference.

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

All CNAPS.ai MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?