pixiv-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTPS_PROXY | No | HTTP proxy to use together with NODE_USE_ENV_PROXY=1. | |
| PIXIV_COOKIE | No | Web login cookie, added to the Cookie of web AJAX requests. | |
| PIXIV_LLM_TAGS | No | Optional: set to 1 to send unmapped Chinese words to an OpenAI-compatible model to translate them into Pixiv tags. | |
| PIXIV_MCP_HOME | No | Data directory, default ~/.pixiv-mcp (Windows: C:\Users\<you>\.pixiv-mcp). Stores history, metadata, and the dynamic tag table. | ~/.pixiv-mcp |
| PIXIV_LLM_MODEL | No | The model used by PIXIV_LLM_TAGS, e.g. gpt-4o-mini. | |
| PIXIV_MEDIA_DIR | No | Image directory, default $PIXIV_MCP_HOME/media. | $PIXIV_MCP_HOME/media |
| PIXIV_PHPSESSID | No | Web login session ID, added to the Cookie of web AJAX requests. | |
| PIXIV_TIMEOUT_MS | No | Timeout for a single request in ms, default 15000 (downloads use twice this). | 15000 |
| PIXIV_COOLDOWN_MS | No | Cooldown per session, default 15000; set 0 to disable. | 15000 |
| PIXIV_LLM_API_KEY | No | The API key used by PIXIV_LLM_TAGS, e.g. sk-... | |
| NODE_USE_ENV_PROXY | No | Set to 1 together with HTTPS_PROXY when an HTTP proxy is needed (supported by Node >= 24 native fetch); image downloads also go through the proxy. | |
| PIXIV_CACHE_MAX_MB | No | Local image cache size limit in MB, evicting least recently used when exceeded, default 512. | 512 |
| PIXIV_LLM_BASE_URL | No | The endpoint used by PIXIV_LLM_TAGS, e.g. https://api.openai.com/v1. | |
| PIXIV_MAX_IMAGE_MB | No | Maximum size of a single original image in MB, default 50. | 50 |
| PIXIV_REFRESH_TOKEN | No | Pixiv refresh token. When set and PIXIV_PROXY_BASE_URL is not set, app-api is used (recommended; R-18 requires login). | |
| PIXIV_PROXY_BASE_URL | No | Reverse proxy origin of www.pixiv.net (paths same as web AJAX). If set, the web interface is always used. | |
| PIXIV_DOWNLOAD_CONCURRENCY | No | Global number of simultaneous downloads, default 2. | 2 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pixiv_searchA | 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。 |
| pixiv_illust_detailA | 按 PID 读取作品元数据(标题、画师、标签、收藏、页数、原图地址、分级),并按同一套黑/灰名单规则给出 compliant 结论。不下载。 |
| pixiv_downloadA | 按 PID 下载原图到本地目录(PIXIV_MEDIA_DIR),返回每页的文件绝对路径与作品元数据。不合规(黑名单/未放行的灰名单/AI/动图)的作品拒绝下载。最多 10 页,下载并发受 PIXIV_DOWNLOAD_CONCURRENCY 限制。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Search (by tags/character), download (by PID), and detail (by PID) have mostly distinct entry points, and descriptions make the download-vs-detail split clear. However, search also returns metadata and file paths, overlapping somewhat with the other two, so an agent may occasionally pick search when it really wants a direct PID fetch.
All tools share a consistent `pixiv_` prefix, but the suffixes mix verbs (`search`, `download`) with a noun phrase (`illust_detail`). Still readable and predictable in practice, just not a uniform verb_noun pattern.
Three tools is on the thin side for a Pixiv illustration workflow, though each has a clear role (search, fetch by PID, download by PID). It is borderline minimal rather than obviously under-scoped.
Core flows—search by tag, inspect by PID, download by PID—are covered with consistent filtering semantics. Notable gaps remain: no way to list or browse an artist's works, no ranking/related/tag-suggestion lookup, and no session or blacklist management operations.