New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pixeval MCP

by Pixeval in Pixeval/Pixeval

“Pixeval MCP 维护指南。仅当修订 MCP 功能相关时需要读取并遵守。”

— description from SKILL.md by Pixeval
GPL-3.0Auto-check passedAgent Workflows

Install Pixeval MCP

skills CLI
$ npx skills add Pixeval/Pixeval --skill pixeval-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Pixeval/Pixeval pixeval-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Pixeval/Pixeval.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pixeval-mcp .claude/skills/pixeval-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pixeval-mcp
GitHub stars
3.2k
Token cost
~608 tokens
SKILL.md length
186 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
GPL-3.0

At a glance

  • SKILL.md covers 架构边界, 工具设计, 缓存约定 and 权限与设置, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Pixeval MCP is a skill in Pixeval/Pixeval (3.2k stars). Its SKILL.md is about 608 tokens. Licence: GPL-3.0.

What it can do on your machine

Read from SKILL.md and the folder at commit 30f113f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pixeval MCP loads about 608 tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 186 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~13
When it runs · the whole SKILL.md, loaded when a task matches
~608

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Pixeval/Pixeval at commit 30f113f, republished under its GPL-3.0 licence (© Pixeval). 186 words, ~608 tokens.

Download SKILL.mdSave it as .claude/skills/pixeval-mcp/SKILL.md (or your agent's skills folder).
name
pixeval-mcp
description
Pixeval MCP 维护指南。仅当修订 MCP 功能相关时需要读取并遵守。

Pixeval MCP

先遵守项目的 tools、code-style、format-style skill；C# 语义查询、格式化、构建优先用 Rider MCP。

架构边界

  • MCP 是 Pixeval GUI 进程内的 Streamable HTTP 服务，不发布独立 exe，不使用环境变量，监听固定为 127.0.0.1:{port}/mcp。
  • src/Pixeval.Mcp 放协议层：工具、资源、DTO、JSON source generation、cursor store、IPixevalMcpRuntime。它不能引用主项目。
  • 主项目实现运行时能力，位置在 src/Pixeval/Models/McpServer。需要 Pixeval 设置、下载、历史、扩展、缓存、HTTP client、日志时，通过 IPixevalMcpRuntime 暴露。
  • MCP 仅 Desktop 启动；不要为了 Browser/WASM 改 MCP 代码，除非用户明确要求。
  • 工具名不要加 pixeval_ 共同前缀，不留兼容别名，不保留旧方法名。

工具设计

  • 优先返回专用 DTO，不直接把 Mako model 暴露为 MCP 输出。DTO 的转换方法放在对应 DTO 类里，例如 FromWork、FromRuntime。
  • 工具参数能用枚举就用枚举，优先使用 Mako 里的枚举或已有 Pixeval MCP 枚举；不要用 string 再手写 parser。STJ enum 输出以 snake_case/camelCase 能支持的命名为准，不额外维护宽松解析表。
  • count 表示本次最多返回多少条，默认 20，使用 PixevalMcpHelpers.ClampCount 限制在 1..100。不要再引入 limit。
  • 远程连续列表必须用 cursor：首个工具返回 hasMore/nextCursor，继续读取统一走 more(cursor, count)，不要让 AI 重复传原查询条件。
  • Cursor token 是 Pixeval 本地状态，形如 pixeval:{kind}:{engineGuid:N}；不要使用 Pixiv 官方分页语义。
  • 列表工具如果支持 workFilter，筛选表达式错误时返回带 diagnostics 的结构化结果，不要静默返回空列表。
  • 看起来轻量的工具不要隐式做大量远程详情请求。批量 works/users 这种显式 get-by-id 例外；其他工具若会下载原图、读取正文、批量加载 Pixiv 命中，必须通过清晰参数或工具名表达。

缓存约定

  • 所有拿到 WorkBase、User、UserBasicInfo 的列表/cursor 路径，应尽量调用 runtime cache：CacheWorks、CacheUsers、CacheUserInfos。
  • 后续按 id 操作必须优先走 runtime getter：GetWorkAsync、GetIllustrationAsync、GetNovelAsync、GetUserAsync、GetUserBasicInfoAsync。不要直接调用 Mako get-by-id 绕过缓存。
  • 写操作需要按 id 使用作品/用户时，也先用 runtime getter；例如下载、稍后看、关注、订阅。收藏可直接调用 Mako bookmark API，不要为了收藏先拉作品详情。
  • 二进制资源和正文读取本身可能很重；可以缓存元数据，但不要把大二进制内容塞进普通模型 cache，除非用户明确要求并设计容量上限。

权限与设置

  • 写工具默认由 Pixeval MCP 设置控制，调用前必须 EnsureWriteToolsEnabled。
  • 只读工具可以读取 Pixeval 本地状态，但不要暴露登录 token、cookie、代理地址、SauceNAO key、扩展设置值或不必要的绝对本机路径。
  • settings_summary 只能返回脱敏摘要；新增设置摘要字段时优先在 DTO/扩展方法里集中转换。
  • 端口和启用状态应能通过 dispose/restart 内部 server 动态生效；不要要求重启 Pixeval，除非底层生命周期无法避免。

JSON 与文档

  • 新 DTO、枚举、工具返回类型要加入 PixevalMcpJsonContext，保持 AOT/trim 友好。
  • 工具返回保持 TextContentBlock JSON + StructuredContent 模式。
  • 工具参数描述不要重复枚举可选值；schema 已经会暴露 enum。
  • HelpPage 的工具列表应从 MCP tools/list 用 STJ DTO 解析，不要手写字符串解析。
  • 涉及下载宏、筛选语句、扩展时，工具描述中提醒 help 可查看现有文档；不要在工具描述里复制完整语法。

验证

  • 修改 MCP 后至少构建 src/Pixeval.Mcp/Pixeval.Mcp.csproj 和 src/Pixeval/Pixeval.csproj。
  • 检查工具 schema 时确认没有旧工具名、手写 enum parser、未加入 source-gen 的 DTO。

© Pixeval, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/pixeval-mcp of Pixeval/Pixeval.

Open the folder on GitHubat commit 30f113f

Compare with similar skills

Pixeval MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pixeval MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pixeval MCP this skillPixeval/Pixeval3.2k—~608Automated safety check: PassGPL-3.0
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from Pixeval/Pixeval

  • I18n

    Pixeval/Pixeval

    Pixeval 国际化资源维护规范，涵盖用户可见字符串、JSON/Markdown 资源、XAML/C 引用、非默认语言增删规则以及 Language.tt 生成验证。Use when adding, moving, removing, or changing localized text in Pixeval.

    3.2k GitHub stars~349 tokensUpdated 2 days ago
    Auto-check passed

  • Format Style

    Pixeval/Pixeval

    工程代码格式化风格指引

    3.2k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Code Style

    Pixeval/Pixeval

    工程代码编写风格指引（不含简单的格式化风格）

    3.2k GitHub stars~730 tokensUpdated 2 days ago
    Auto-check passed

  • Tools

    Pixeval/Pixeval

    代码工具选择

    3.2k GitHub stars~217 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Pixeval MCP

How do I install Pixeval MCP in Claude Code?

Run `npx skills add Pixeval/Pixeval --skill pixeval-mcp -a claude-code`. Or copy the skill folder (.agents/skills/pixeval-mcp in Pixeval/Pixeval) into .claude/skills/pixeval-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Pixeval MCP in Codex?

Run `npx skills add Pixeval/Pixeval --skill pixeval-mcp -a codex`. Or copy the skill folder (.agents/skills/pixeval-mcp in Pixeval/Pixeval) into .agents/skills/pixeval-mcp in your project. Codex loads it when a task matches its description.

Can I use Pixeval MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Pixeval/Pixeval --skill pixeval-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pixeval-mcp, .gemini/skills/pixeval-mcp, .github/skills/pixeval-mcp and .opencode/skills/pixeval-mcp in your project.

What does Pixeval MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Pixeval MCP is instructions for the agent only.

Does Pixeval MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pixeval MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pixeval MCP use?

Pixeval MCP is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pixeval MCP use?

About 608 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pixeval MCP?

Skills that share tags, products or a category with Pixeval MCP: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pixeval MCP?

Pixeval (a GitHub organization) maintains it in Pixeval/Pixeval, which has 3,164 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

Source: Pixeval/Pixeval on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.