Skip to main content
Glama
deenesjakoruzh
SeeYangZhi

heroicons-mcp

by SeeYangZhi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

heroicons-mcp

一个模型上下文协议 (MCP)服务器，将Heroicons作为 LLM 和代理应用程序的资源和工具公开。使用 Bun 和 MCP TypeScript SDK 构建。

Heroicons 是什么？

Heroicons是一个流行的手工 SVG 图标库，由 Tailwind CSS 的开发者设计。这些图标提供多种样式（轮廓、实心），易于集成到 Web 项目中。

Related MCP server: SupaUI MCP Server

什么是 MCP？

模型上下文协议 (MCP)是 AI 工具从其主要训练数据之外的来源请求特定上下文的标准。

该 MCP 服务器允许 AI 编码助手和其他代理应用程序访问有关 Heroicons 的信息，从而提供更好的帮助和图标搜索功能。

特征

  • 将 Heroicons 作为 MCP 资源公开（轮廓和实心样式）

  • 提供按名称或关键字搜索图标的工具

  • 允许列出所有图标或特定样式的图标

  • 准备与 Claude Desktop 和其他 MCP 客户端集成

  • 可以作为 HTTP 服务器或基于 stdio 的 MCP 服务器运行

先决条件

入门（开发）

1. 克隆存储库

git clone https://github.com/SeeYangZhi/heroicons-mcp.git
cd heroicons-mcp

2.安装 Bun（如果没有）

参考Bun官方安装指南。
安装完成后，重新启动终端并检查：

bun --version

3.安装依赖项

bun install

4. 构建项目

这会在build目录中将 TypeScript 源编译为 JavaScript。

bun run build

用法

HTTP 模式

您可以使用npx运行 HTTP 服务器：

npx heroicons-mcp

这将启动 HTTP 服务器（默认为端口 3000，如src/http.ts中所定义）。

或者全局安装：

npm install -g heroicons-mcp

然后运行：

heroicons-mcp

标准输入输出模式

npx heroicons-mcp --stdio
# or if installed globally
heroicons-mcp --stdio

本地开发

运行 MCP 服务器主要有两种方式：

1. HTTP模式

适用于支持通过 HTTP 进行通信的客户端。

对于开发（使用 Bun）：

bun run start
# or directly
bun run src/entry.ts

这将运行在src/entry.ts中定义的服务器，默认为 HTTP 模式。

2. Stdio 模式

通常用于与 Claude Desktop 或 MCP Inspector 等工具直接集成，通过标准输入/输出进行通信。

对于开发（使用 Bun）：

bun run src/entry.ts --stdio

使用AI工具进行配置

例如：Claude Desktop

要在Claude Desktop中使用此 MCP 服务器：

  1. 打开您的 Claude Desktop 配置文件：

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

（或者使用您喜欢的编辑器）2. 将服务器添加到mcpServers部分。

选项 A：通过npx ：

{
  "mcpServers": {
    "heroicons": {
      "command": "npx",
      "args": ["heroicons-mcp", "--stdio"]
    }
  }
}

选项 B：直接指向构建输出（确保您已使用bun run build构建了项目）：

{
  "mcpServers": {
    "heroicons": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/TO/heroicons-mcp/build/entry.js", "--stdio"]
    }
  }
}

将/ABSOLUTE/PATH/TO/heroicons-mcp/build/entry.js替换为您构建的entry.js文件的实际绝对路径。

  1. 保存文件并重新启动 Claude Desktop。

  2. 您现在应该可以在 Claude 的工具面板中看到“heroicons”服务器。

注意： npx heroicons-mcp --stdio命令是 stdio 模式的推荐方法。

可用工具 (MCP)

该 MCP 服务器向 AI 编码助手公开以下工具：

  1. 列出所有图标

  • 描述：列出所有可用的英雄图标，可选择按样式（轮廓、实心）进行过滤。

  • 参数： style （可选：“outline”|“solid”）

  1. 搜索图标

  • 描述：按名称或关键字搜索所有样式的 Heroicons。

  • 参数： query （字符串）、 style （可选：“轮廓”|“实心”）

  1. 获取图标使用示例

  • 描述：检索特定图标的 JSX 示例用法。

  • 参数： name （字符串）、 style （字符串：“outline”|“solid”）

示例用法

AI 工具可能这样使用此 MCP 服务器：

  1. 用户询问 AI 工具：“从 Heroicons 中帮我找一个‘用户’图标，最好是实心的。”

  2. AI工具调用search_icons ：

  • query ：“用户”

  • style ：“纯色”

  1. MCP 服务器响应匹配的实心 Heroicon 列表（例如， UserIcon 、 UserCircleIcon 、 UserPlusIcon ）。

  2. 用户询问工具：“显示 UserIcon 的使用示例”。

  3. AI工具调用get_icon_usage_examples ：

  • name ：“用户图标”

  • style ：“纯色”

  1. MCP 服务器使用 JSX 代码示例进行响应：

import { UserIcon } from "@heroicons/react/24/solid";

function Example() {
  return (
    <div>
      <UserIcon className="w-6 h-6 text-blue-500" />
    </div>
  );
}

使用 Inspector 在本地测试 MCP

您可以使用MCP Inspector在本地测试 MCP 服务器（stdio 模式）。

首先，确保项目已构建：

bun run build

然后启动 Inspector 并使用带有--stdio标志的node ./build/entry.js命令将其连接到您的服务器：

npx @modelcontextprotocol/inspector node ./build/entry.js --stdio

这将打开 Inspector 界面，允许您以交互方式测试 MCP 服务器公开的资源和工具。

开发脚本

  • bun run dev ：以 HTTP 模式启动服务器进行开发（使用src/entry.ts ）。

  • bun run dev:stdio ：启动 stdio MCP 服务器进行开发（使用src/entry.ts --stdio ）。

  • bun run build ：将 TypeScript 编译为 JavaScript（在build/中输出）。

  • bun run lint ：使用 ESLint 检查代码库。

资源

执照

麻省理工学院

Available Tools

3 tools
get_icon_usage_examplesB

Get usage examples for an icon

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesIcon component name, e.g. BeakerIcon
styleYesIcon style: solid or outline

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but does not reveal any behavioral traits such as whether it's a read-only operation, potential rate limits, error conditions, or the format of returned examples. For a tool with no annotations, this is a significant gap, warranting a score of 2.

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

Conciseness5/5

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it easy for an agent to parse quickly. This optimal conciseness earns a score of 5.

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

Completeness3/5

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

Given the tool's moderate complexity (2 required parameters) and no output schema, the description is minimally adequate. It covers the basic purpose but lacks details on behavioral traits, usage context, and output format, which are important for an agent to use the tool effectively. Without annotations or an output schema, the description should do more, resulting in a score of 3.

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?

The schema description coverage is 100%, with clear descriptions for both parameters ('name' and 'style'), including an enum for 'style'. The description does not add any meaning beyond what the schema provides, such as explaining how 'name' relates to icon components or providing examples of usage. Given the high schema coverage, the baseline score of 3 is appropriate.

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?

The description clearly states the verb 'Get' and the resource 'usage examples for an icon', making the purpose understandable. However, it does not explicitly differentiate from sibling tools like 'list_all_icons' or 'search_icons', which might also involve icons but serve different functions. This clarity without sibling distinction justifies a score of 4.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives such as 'list_all_icons' or 'search_icons'. There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage based on the tool name alone. This lack of explicit guidelines results in a score of 2.

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

list_all_iconsB

List all icons from the heroicons library, optionally filtered by style

ParametersJSON Schema
NameRequiredDescriptionDefault
styleNoIcon style: solid or outline (optional)

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions listing and optional filtering but doesn't describe key behaviors such as pagination, rate limits, authentication requirements, or what the output format looks like (e.g., list of icon names, metadata). For a tool with no annotations, this leaves significant gaps in understanding how it operates.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core purpose ('List all icons from the heroicons library') and adds an optional feature ('optionally filtered by style'). There is no wasted text, and it's appropriately sized for a simple tool.

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

Completeness3/5

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

Given the tool's low complexity (1 optional parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose and parameter intent but lacks details on behavioral aspects like output format or usage constraints. For a listing tool, this is borderline acceptable but could be improved with more context.

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 description coverage is 100%, with the single parameter 'style' fully documented in the schema (including enum values 'solid' or 'outline'). The description adds minimal value beyond the schema by mentioning 'optionally filtered by style', which aligns with the schema but doesn't provide additional context like default behavior if omitted or how filtering is applied.

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?

The description clearly states the verb 'List' and resource 'all icons from the heroicons library', which provides a specific purpose. However, it doesn't explicitly differentiate from sibling tools like 'search_icons' or 'get_icon_usage_examples', which likely have different functions (searching vs listing, or getting usage examples vs listing icons).

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

Usage Guidelines3/5

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

The description implies usage by mentioning 'optionally filtered by style', suggesting this tool is for listing icons with optional style filtering. However, it doesn't provide explicit guidance on when to use this tool versus alternatives like 'search_icons' (which might allow more complex queries) or 'get_icon_usage_examples' (which focuses on examples rather than listing).

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

search_iconsB

Search for icons from heroicons by name or category

ParametersJSON Schema
NameRequiredDescriptionDefault
categoryNoCategory to filter by (optional)
limitNoMax results to return
queryYesSearch term for icon name or category
styleNoIcon style: solid or outline

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't mention rate limits, authentication needs, response format, pagination, or error handling. The description only states the basic functionality without operational context.

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

Conciseness5/5

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

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for this tool's complexity and front-loads the core functionality without unnecessary elaboration.

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

Completeness3/5

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

For a search tool with no annotations and no output schema, the description is minimally adequate. It covers the basic purpose but lacks details about return values, error conditions, and behavioral constraints that would be helpful for an AI agent.

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 description coverage is 100%, so the schema fully documents all parameters. The description adds minimal value by mentioning 'name or category' search, which aligns with the 'query' parameter but doesn't provide additional semantic context beyond what's in the 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?

The description clearly states the action ('Search for icons') and resource ('from heroicons'), specifying the search scope ('by name or category'). It distinguishes from 'list_all_icons' by implying filtering, but doesn't explicitly differentiate from 'get_icon_usage_examples'.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus siblings is provided. The description implies filtering capabilities but doesn't specify scenarios where search_icons is preferred over list_all_icons or get_icon_usage_examples.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedget_icon_usage_examples
    • First observedlist_all_icons
    • First observedsearch_icons
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: listing all icons, searching icons by criteria, and getting usage examples for a specific icon. There is no overlap in functionality, making it easy for an agent to select the right tool without confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_icon_usage_examples, list_all_icons, search_icons) with clear, descriptive verbs. The naming is uniform and predictable across the set.

Tool Count5/5

With 3 tools, this server is well-scoped for its purpose of accessing a heroicons library. Each tool serves a distinct and essential function, making the count appropriate without being too thin or heavy.

Completeness5/5

The tool set provides complete coverage for the domain: listing icons, searching icons, and getting usage examples. This covers the core workflows for accessing and utilizing an icon library, with no obvious gaps or dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • hugeicons-mcp

    hugeicons
    A
    license
    A
    quality
    F
    maintenance
    MCP server for Hugeicons integration and documentation This is a TypeScript-based MCP server that provides tools and resources for integrating Hugeicons into various platforms. It implements a Model Context Protocol (MCP) server that helps AI assistants provide accurate guidance for using Hugeicons
    5
    2,051 npm
    26
    MIT

  • PickAPIcon MCP

    Leee62
    A
    license
    B
    quality
    D
    maintenance
    MCP server that allows FE/UI/Designers to retrieve SVG icons via the Iconify API by simply asking LLMs rather than manually searching websites.
    3
    31 npm
    4
    MIT