.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/ip2a/mcpstore
home/mcp-servers/ip2a/mcpstore
ip2a avatar

mcpstore

byip2a· 1 MCP server

Stars

418

Forks

29

Category

AI Agents & MCP

View on GitHub

TL;DR

<table align="center"> <tr> <td> <pre> ███ ███ ██████ ███████ ██████ ████████ ██████ ██████ ███████ ████ ████ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ████ ██ ██ ███████ ██████ ██ ██ ██ ██████ █████ ██ ██ ██ ██ ██

How to install mcpstore?

ip2a/mcpstore
$git clone https://github.com/ip2a/mcpstore

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install mcpstore by running `git clone https://github.com/ip2a/mcpstore`, then use it for the current task and follow its documentation at https://github.com/ip2a/mcpstore.

Files · 1

View on GitHub
README.md
1<div align="center">
2 
3<table align="center">
4 <tr>
5 <td>
6<pre>
7███ ███ ██████ ███████ ██████ ████████ ██████ ██████ ███████
8████ ████ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██
9██ ████ ██ ██ ███████ ██████ ██ ██ ██ ██████ █████
10██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██
11██ ██ ██████ ██ ██████ ██ ██████ ██ ██ ███████
12</pre>
13 </td>
14 </tr>
15</table>
16 
17---
18 
19![GitHub stars](https://img.shields.io/github/stars/ip2a/mcpstore) ![GitHub forks](https://img.shields.io/github/forks/ip2a/mcpstore) ![GitHub license](https://img.shields.io/github/license/ip2a/mcpstore) ![Python versions](https://img.shields.io/pypi/pyversions/mcpstore)
20 
21 
22 
23[English](README_en.md) | [简体中文](README_zh.md)
24 
25 
26[文档](https://ip2a.github.io/mcpstore/) | [快速使用](###简单示例)
27 
28</div>
29 
30### mcpstore 是什么?
31 
32开发者最佳的mcp管理包 快速维护mcp服务并应用
33 
34### 快速开始
35 
36```bash
37pip install mcpstore
38```
39 
40### Rust-first 架构
41 
42当前 `mcpstore` 以 Rust 作为唯一真实运行时:
43 
44- `mcpstore api` 由 Rust 二进制直接启动完整 HTTP API 服务
45- `mcpstore mcp-server` 由 Rust 二进制直接暴露 MCP Server,支持 `stdio` 和 `streamable-http`
46- Python 包主要提供 PyO3 store facade、稳定的 Python SDK 入口,以及 Python 生态 adapter
47 
48如果你只想把 `mcpstore` 当成独立服务使用,优先直接调用 Rust CLI:
49 
50```bash
51mcpstore api --config-path ./mcp.json --port 18200
52mcpstore mcp-server --config-path ./mcp.json
53mcpstore mcp-server --config-path ./mcp.json --transport streamable-http --port 18300 --path /mcp
54```
55 
56### 简单示例
57 
58一切的开始:初始化一个store
59 
60```python
61from mcpstore import MCPStore
62store = MCPStore.setup_store()
63```
64 
65现在你获得了一个 `store`,利用`store`去使用你的MCP服务,`store` 会维护和管理这些 MCP 服务。
66 
67#### 给store添加第一个服务
68 
69```python
70#在上面的代码下面加入
71store.for_store().add_service({"mcpServers": {"mcpstore_wiki": {"url": "https://example.com/mcp"}}})
72store.for_store().wait_service("mcpstore_wiki")
73```
74 
75`add_service`方法支持多种mcp服务配置格式,。`wait_service`用来等待服务就绪。
76 
77#### 将mcp适配转为langchain需要的对象
78 
79```python
80#在上面的代码下面加入
81tools = store.for_store().for_langchain().list_tools()
82print("loaded langchain tools:", len(tools))
83```
84 
85轻松将mcp服务转为langchain可以直接使用的tools列表
86 
87##### 框架适配
88 
89积极支持更多的框架
90 
91| 已支持框架 | 获取工具 |
92| --- | --- |
93| LangChain | `tools = store.for_store().for_langchain().list_tools()` |
94| LangGraph | `tools = store.for_store().for_langgraph().list_tools()` |
95| AutoGen | `tools = store.for_store().for_autogen().list_tools()` |
96| CrewAI | `tools = store.for_store().for_crewai().list_tools()` |
97| LlamaIndex | `tools = store.for_store().for_llamaindex().list_tools()` |
98 
99#### 代码中使用 以langchain为例
100 
101```python
102#添加上面的代码
103from langchain.agents import create_agent
104from langchain_openai import ChatOpenAI
105llm = ChatOpenAI(
106 temperature=0,
107 model="your-model",
108 api_key="sk-*****",
109 base_url="https://api.xxx.com"
110)
111agent = create_agent(model=llm, tools=tools, system_prompt="你是一个助手,回答的时候带上表情")
112events = agent.invoke({"messages": [{"role": "user", "content": "mcpstore怎么添加服务?"}]})
113print(events)
114```
115如你所见。这里的langchain的agent可以正常的调用你通过`sotre`管理的mcp服务了。
116 
117 
118 
119 
120#### 为 Agent 分组
121 
122使用 `for_agent(agent_id)` 实现分组
123 
124```python
125#不同的agent需要不同的mcp的集合
126 
127agent_id1 = "agent1"
128store.for_agent(agent_id1).add_service({"name": "mcpstore_wiki", "url": "https://example.com/mcp"})
129 
130agent_id2 = "agent2"
131store.for_agent(agent_id2).add_service({"name": "gitodo", "command": "uvx", "args": ["gitodo"]})
132 
133agent1_tools = store.for_agent(agent_id1).list_tools()
134 
135agent2_tools = store.for_agent(agent_id2).list_tools()
136```
137 
138`store.for_agent(agent_id)` 与 `store.for_store()` 镜像大部分函数接口, `agent` 的分组是 `store` 的逻辑子集。
139 
140通过为不同 `agent` 隔离mcp服务,避免上下文过长,并由 `sotre` 统一维护。
141 
142#### Rust API 与 MCP Server
143 
144当前推荐直接使用 Rust CLI 暴露服务,而不是再依赖历史 Python hub 接口:
145 
146```bash
147# 启动 Rust HTTP API
148mcpstore api --config-path ./mcp.json --host 127.0.0.1 --port 18200
149 
150# 以 stdio 启动 Rust MCP Server
151mcpstore mcp-server --config-path ./mcp.json
152 
153# 以 streamable-http 启动 Rust MCP Server
154mcpstore mcp-server --config-path ./mcp.json --transport streamable-http --host 127.0.0.1 --port 18300 --path /mcp
155```
156 
157Python 侧已不再提供嵌入式 API server;请直接使用 Rust CLI 启动服务。
158 
159 
160 
161 
162#### 常用接口
163 
164| 动作

Preview

ip2a/mcpstoreip2a/mcpstore
Repoip2a/mcpstore
TypeMCP Servers
CategoryAI Agents & MCP
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

MCPfastmcpmcp

Related

6 picks
Type
  1. langchain-ai avatarlangchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.MCP ServersJul 20267.0M3.6k
  2. openclaw avatarmcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.MCP ServersJul 20262.5M4.8k
  3. sparfenyuk avatarmcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.MCP ServersJul 20262.2M2.7k
  4. sooperset avatarmcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.MCP ServersJul 20261.7M5.6k
  5. open-webui avataropen-webuiOpen WebUIMCP ServersJul 20261.4M147k
  6. dyoshikawa avatarrulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsMCP ServersJul 2026889k1.3k