Skip to main content
Glama
pixiv-mcp

pixiv-mcp

by go0le

Pixiv 插画搜索

pixiv_search

Search Pixiv illustrations by character name or tags, apply content filters, and download original images while returning local paths and metadata.

Instructions

按角色名/标签搜索 Pixiv 高质量插画,下载原图到本地并返回文件路径与元数据。多个标签是 AND(全部要在作品标签或标题里命中)。自动过滤:同作品互斥角色蹭标签、AI 生成(aiType=2)、动图、黑名单(BL/猎奇/福瑞/抽象整活等,请求里含黑名单词会被整次拒绝)。灰名单(R-18 及特定玩法)默认避开,只有 r18 / allow_gray 明确放行时才放行且必须真有。R-18 只认 Pixiv 官方 xRestrict。按 1 年半衰期收藏数排序,同一 session 不重复出图;同一 session 有冷却(默认 15 秒)。中文角色名有内置映射;不在映射里的词建议调用方先翻成 Pixiv 常用日文标签再传入(如 水手服→セーラー服)。给用户展示时,输出内容只能有图片和 caption(🎨 画师:xxx):禁止附带作品标题、PID、Pixiv 链接、file:// 链接、本地路径或任何说明文字。tags 只能取自用户本条消息明确写出的词,r18 / allow_gray 仅当本条消息明文要求时才设置,不得从历史对话继承。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tags": "<tags>"
    },
    "name": "pixiv_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
r18No用户明确要求 R-18 时为 true(需要登录凭据)
tagsYes标签数组,或空格分隔字符串。例: ["信浓","泳装"] 或 "信濃(アズールレーン) 水着"
countNo张数 1-5,默认 1
sessionNo会话键:去重历史与冷却按此隔离,默认 "default"
allow_grayNo显式放行的灰名单类别(默认全部避开)。只有用户明确点名时才传。放行的类别作品必须真的具备;其余灰名单仍拒绝。可选: r18(官方 R-18) / oral(口交) / creampie(中出) / paizuri(乳交) / footjob(足交) / ahegao(阿黑颜) / sex(性交)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.0
    • changedInput schema / properties / count / description
      Previous value: -"张数 1-3,默认 1"New value: +"张数 1-5,默认 1"
    • changedInput schema / properties / count / maximum
      Previous value: -3New value: +5
  2. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses automatic filtering (mutually exclusive character tags, aiType=2, animations, blacklist with whole-request rejection), gray-list defaults, R-18 detection via official xRestrict, favorite-count sorting with a 1.5-year half-life, per-session deduplication and a 15-second cooldown. The output contract (file paths + metadata) and display restrictions are also stated.

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 core search-and-download purpose is front-loaded and the dense single paragraph is largely earned by filter and safety rules. Some padding exists — the display-output prohibition is stated at length and partially restates the caption format — but nothing is seriously misplaced.

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 five-parameter tool with no output schema, the description covers return values (file path and metadata), ordering, per-session state and cooldown, rejection conditions, and even how results may be presented. An agent has everything needed to call it correctly and to avoid the common failure modes.

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

Parameters3/5

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

Schema coverage is 100%, so all five parameters are already documented; the description adds real meaning on top (multiple tags are AND across work tags or title, r18 only counts Pixiv official xRestrict, allow_gray categories must be genuinely present) but not for every parameter. Session, count and the 8-tag ceiling are left to the schema, which is acceptable given full coverage.

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 (搜索 Pixiv 插画) plus concrete side effects (下载原图、返回文件路径与元数据), and the tag-AND semantics make the search behavior unambiguous. It does not, however, distinguish itself from the sibling pixiv_download even though it also downloads files, leaving overlap for the agent to infer.

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?

Gives explicit when/when-not rules: gray-list categories only pass when the user names them this turn, r18/allow_gray must not be inherited from history, tags must come from the current user message, and non-mapped Chinese terms should be translated to Pixiv Japanese tags first. These are precisely the conditions that would otherwise cause an agent to mis-call the tool.

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