Skip to main content
Glama
ComicK MCP Server

ComicK MCP Server

by edmer664

search_comics

Search the ComicK database by natural-language description, title, or filters to find manga, manhwa, and manhua matching genres, status, country, and tags.

Instructions

Search the ComicK database using a natural-language query, title keyword, or structured filters.

Natural-language descriptions (e.g., "I want a badass MC manhwa with swords and magic") are automatically parsed into country ('kr'/'jp'/'cn'), genres, category tags, status, and sort filters and executed across multi-pass queries so you get relevant ranked matches instead of zero literal-title matches.

Args: query: Natural-language description (e.g. "I want a badass MC manhwa with swords and magic") or comic title (e.g. "Solo Leveling"). genres: Comma-separated genre slugs (e.g. "action,fantasy,magic,martial-arts"). tags: Comma-separated category/tag slugs (e.g. "sword-and-sorcery-magic,overpowered-protagonist,swordsman"). country: Comma-separated origin codes or names ('kr' / 'manhwa', 'jp' / 'manga', 'cn' / 'manhua'). status: Publication status ('ongoing'/'1', 'completed'/'2', 'cancelled'/'3', 'hiatus'/'4'). demographic: Comma-separated demographics ('shounen'/'1', 'shoujo'/'2', 'seinen'/'3', 'josei'/'4'). sort: Sort field ('user_follow_count'/'popular', 'rating', 'average_rating', 'view', 'uploaded', 'created_at'). min_chapters: Minimum chapter count (e.g. 50). excluded_genres: Comma-separated genre slugs to exclude. excluded_tags: Comma-separated category/tag slugs to exclude. page: 1-based pagination page (default 1). limit: Max results to return (default 15, max 50).

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_comics"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
sortNo
tagsNo
limitNo
queryNo
genresNo
statusNo
countryNo
demographicNo
min_chaptersNo
excluded_tagsNo
excluded_genresNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and mostly meets it: it reveals that NL queries are auto-parsed into country/genres/tags/status/sort and executed as multi-pass queries with ranked output. It also states defaults and the 50-result cap. It omits any statement about read-only nature, rate limits, or error/empty-result behavior.

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?

The opening paragraph is front-loaded with capability and rationale, followed by a scannable per-argument list, which suits a 12-parameter tool. A few lines restate defaults already present in the schema (page=1, limit=15), a minor redundancy. Overall, very little waste.

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

Completeness4/5

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

For a 12-parameter, zero-annotation search tool, the definition covers input semantics, parsing behavior, ranking intent, and pagination limits, and the return shape is covered by the existing output schema. Remaining gaps are operational details: how multiple filter parameters are combined, and what an empty or no-match query returns.

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

Parameters5/5

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

Schema coverage is 0%, so the description must carry all parameter meaning — and it does, documenting every one of the 12 parameters with types, examples, and accepted aliases ('kr'/'manhwa', 'ongoing'/'1', 'popular'/'user_follow_count'). The comma-separated convention and the exclusion semantics of excluded_genres/excluded_tags are spelled out. This fully compensates for the bare schema.

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

Purpose4/5

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

States a specific verb and resource (search the ComicK database) and enumerates the three input modes: natural-language, title keyword, and structured filters. It also discloses the distinctive multi-pass parsing behavior that separates it from a plain title lookup. It does not, however, differentiate itself from the sibling recommend_comics_by_prompt, which plausibly also accepts a natural-language prompt, leaving that boundary ambiguous.

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

Usage Guidelines4/5

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

Gives concrete worked examples for each mode of use (a prose request vs. a title like 'Solo Leveling'), so an agent can infer when to send which kind of input. It also explains why NL input is worthwhile ('relevant ranked matches instead of zero literal-title matches'). It stops short of saying when to prefer the recommendation sibling or how filters combine with a NL query.

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